The DOI matches its Crossref record; 140 of the 168 references it cites were found in a registry or an index; 10 of the 54 sources its claims cite were checked for support.
Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing
Open accessAbstract
With the breakthroughs in deep learning, the recent years have witnessed a booming of artificial intelligence (AI) applications and services, spanning from personal assistant to recommendation systems to video/audio surveillance. More recently, with the proliferation of mobile computing and Internet of Things (IoT), billions of mobile and IoT devices are connected to the Internet, generating zillions bytes of data at the network edge. Driving by this trend, there is an urgent need to push the AI frontiers to the network edge so as to fully unleash the potential of the edge big data. To meet this demand, edge computing, an emerging paradigm that pushes computing tasks and services from the network core to the network edge, has been widely recognized as a promising solution. The resulted new interdiscipline, edge AI or edge intelligence (EI), is beginning to receive a tremendous amount of interest. However, research on EI is still in its infancy stage, and a dedicated venue for exchanging the recent advances of EI is highly desired by both the computer system and AI communities. To this end, we conduct a comprehensive survey of the recent research efforts on EI. Specifically, we first review the background and motivation for AI running at the network edge. We then provide an overview of the overarching architectures, frameworks, and emerging key technologies for deep learning model toward training/inference at the network edge. Finally, we discuss future research opportunities on EI. We believe that this survey will elicit escalating attentions, stimulate fruitful discussions, and inspire further research ideas on EI.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
10 of 54 cited sources checked · 4 supported · 0 flagged · accuracy not yet measured
Every source the paper cites for this claim was checked and supports it.
In the paper
“Stamoulis et al. [106] cast the adaptive DNN model selection issue as a hyperparameter optimization problem by taking into account the accuracy and communication constraints imposed by the devices.Then, a Bayesian optimization (BO) is adopted to solve this problem, achieving an improvement by up to 6× in terms of minimum energy per image under accuracy constraints.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > Park et al.
What the sources say
- Supportedcites [106] 106. D. Stamoulis et al., "Designing adaptive neural networks for energy-constrained image classification," in Proc. ACM ICCAD, 2018, Art. no. 23. source
Section 4.1 (p. 4) formulates adaptive CNN design, including network selection, as a hyperparameter optimization problem. Section 4.2 (p. 4) says the authors adapt Bayesian optimization to solve it, and the Conclusion (p. 8) reports up to 6× lower minimum energy per image under accuracy constraints than previously published methods. (LLM, conf=0.94)
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“The result varies with architectures and transfer techniques.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
What the sources say
- Not checked — no full text of the sourcecites [62] 62. R. Sharma, S. Biookaghazadeh, B. Li, and M. Zhao, "Are existing knowledge transfer techniques effective for deep learning with edge devices?" in Proc. IEEE Int. Conf. Edge Comput. (EDGE), Jul. 2018, pp. 42-49. source
- Could not verifycites [44] 44. Q. Chen, Z. Zheng, C. Hu, D. Wang, and F. Liu, "Data-driven task allocation for multi-task transfer learning on the edge," in Proc. IEEE 39th Int. Conf. Distrib. Comput. Syst. (ICDCS), 2019. sourceExperimental — accuracy not yet measured
Section 5.2.2 (p. 6) reports accuracy for one architecture under different distributed-training conditions, but does not compare architectures or transfer-learning techniques. Section 6 (p. 6) calls studies of other DNN architectures future work. Searches for transfer learning and variation across architectures or transfer techniques found no passage addressing the claim. (LLM, conf=0.76)
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesThe cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Cachier can increase responsiveness by 3× or more.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) Edge Caching:
What the sources say
- Could not verifycites [93] 93. U. Drolia, K. Guo, J. Tan, R. Gandhi, and P. Narasimhan, "Cachier: Edge-caching for recognition applications," in Proc. IEEE ICDCS, Jun. 2017, pp. 276-286. sourceExperimental — accuracy not yet measured
The Results section discusses Edgent’s inference latency, but does not report a result for Cachier. Searches for “Cachier” and “responsiveness three times” found no passage supporting a 3× improvement. (LLM, conf=0.77)
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Could not verify
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Data Generated at the Network Edge Need AI to Fully Unlock Their Potential”
- Also stated in: § A. Motivation and Benefits of Edge Intelligence · boosted
“AI will be functionally necessary due to its ability to quickly analyze those huge data volumes and extract insights from them for high-quality decision making.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > A. Motivation and Benefits of Edge Intelligence
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Also stated in: § A. Motivation and Benefits of Edge Intelligence · boosted
In the paper
“Cisco estimates that nearly 850 ZB will be generated by all people, machines, and things at the network edge by 2021 [3].”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > I. I N T R O D U C T I O N
What the sources say
- Not matchedcites [3] 3. Cisco Global Cloud Index: Forecast and Methodology, 2016-2021, White Paper. [Online]. Available: https://www.cisco.com/c/en/us/ solutions/collateral/service-provider/global- cloud-index-gci/white-paper-c11-738085.html
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:hedged· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes- Not matched
In the paper
“Lin et al. [53] observe that 99.9% of the gradient exchange in distributed SGD (DSGD) are redundant, which demonstrates the power of gradient compression.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 3) Gradient Compression:
What the sources say
- Not checked — no full text of the sourcecites [53] 53. Y. Lin, S. Han, H. Mao, Y. Wang, and W. J. Dally, "Deep gradient compression: Reducing the communication bandwidth for distributed training," 2017, arXiv:1712.01887. [Online]. Available: https://arxiv.org/abs/1712.01887 source
Load-bearingStrength:boosted· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIn the paper
“Specifically, while preserving client's own privacy, the training loss can be reduced by sharing the models among clients, comparing to training solely on their own inputs.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > C. Enabling Technologies
What the sources say
- Not checked — no full text of the sourcecites [46] 46. R. Shokri and V. Shmatikov, "Privacy-preserving deep learning," in Proc. 22nd ACM SIGSAC Conf. Comput. Commun. Secur., 2015, pp. 1310-1321. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesA conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Edge Computing Is Able to Prosper AI With Richer Data and Application Scenarios”
- Also stated in: § 2) Edge Computing Is Able to Prosper AI With Richer Data and Application Scenarios: · hedged
“edge computing is proposed to achieve low-latency data processing by sinking the computing capability from the cloud data center to the edge side, i.e., data generation source, which may enable AI processing with high performance.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 2) Edge Computing Is Able to Prosper AI With Richer Data and Application Scenarios:
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Also stated in: § 2) Edge Computing Is Able to Prosper AI With Richer Data and Application Scenarios: · hedged
In the paper
“A flaw of [46] is that it does not consider unbalanced and nonindependent identical distribution (non-IID) data.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > C. Enabling Technologies
What the sources say
- Not checked — no full text of the sourcecites [46] 46. R. Shokri and V. Shmatikov, "Privacy-preserving deep learning," in Proc. 22nd ACM SIGSAC Conf. Comput. Commun. Secur., 2015, pp. 1310-1321. source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIn the paper
“big data have recently gone through a radical shift of data source from the megascale cloud datacenters to the increasingly widespread end devices, e.g., mobile devices and Internetof-Things (IoT) devices.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > I. I N T R O D U C T I O N
What the sources say
- Not matchedcites [3] 3. Cisco Global Cloud Index: Forecast and Methodology, 2016-2021, White Paper. [Online]. Available: https://www.cisco.com/c/en/us/ solutions/collateral/service-provider/global- cloud-index-gci/white-paper-c11-738085.html
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Not matched
- Probably not a substantial claim. 28
- It may state two separate claims as one. 27
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“VGG-16 [19] is trained to a deeper structure of 16 layers consisting of 13 convolution layers and three fully connected layers, requiring 138 million weights and 15.5G MACs to classify the image with a size of 224 × 224.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Convolution Neural Network:
What the sources say
- Partly supportedcites [19] 19. K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," 2014, arXiv:1409.1556. [Online]. Available: https://arxiv.org/abs/1409.1556 sourceExperimental — accuracy not yet measured
Table 1 (p. 3) identifies configuration D as a 16-weight-layer network with a 224 × 224 RGB input, and Table 2 (p. 3) lists 138 million parameters for D. Section 2.1 (p. 2) describes the three fully connected layers. Our copy does not report the claimed 15.5G MACs per image, so that part is unsupported. (LLM, conf=0.88)
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Partly supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“In particular, an update aggregation protocol named FedCS is developed to allow the centralized server to aggregate as many client updates as possible and to accelerate performance improvement in ML models.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 2) Aggregation Frequency Control:
What the sources say
- Could not verifycites [52] 52. T. Nishio and R. Yonetani, "Client selection for federated learning with heterogeneous resources in mobile edge," 2018, arXiv:1804.08333. [Online]. Available: https://arxiv.org/abs/ 1804.08333 sourceExperimental — accuracy not yet measured
The Introduction (p. 2) describes pruning, quantization, and Huffman coding, while §6.3 (pp. 9–10) discusses inference speedups from compression. Searches for FedCS, client-update aggregation, and federated client selection found no passage addressing the claimed protocol or its effect on model improvement. (LLM, conf=0.76)
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Could not verify
Every source the paper cites for this claim was checked and supports it.
In the paper
“The optimization in [45] emphasizes the properties of unbalanced and non-IID since the distributed data may come from various sources.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > C. Enabling Technologies
What the sources say
- Supportedcites [45] 45. H. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. Y. Arcas, "Communication-efficient learning of deep networks from decentralized data," 2016, arXiv:1602.05629. [Online]. Available: https://arxiv.org/abs/1602.05629 source
The Introduction (p. 2) explicitly says the work emphasizes the non-IID and unbalanced properties of federated optimization. It explains that clients’ data reflect different users’ device usage and that users contribute varying amounts of data, supporting the citing sentence’s explanation of why those properties arise. (LLM, conf=0.94)
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“when moving a tremendous amount of data across the wide area network (WAN), both monetary cost and transmission delay can be prohibitively high, and the privacy leakage can also be a major concern [5].”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > I. I N T R O D U C T I O N
What the sources say
- Could not verifycites [5] 5. Q. Pu et al., "Low latency geo-distributed data analytics," in Proc. ACM SIGCOMM, 2015, pp. 421-434. sourceExperimental — accuracy not yet measured
The Introduction and Section 6 (Advantages and disadvantages; page numbers unavailable) discuss generative models and their computational properties, not transferring large datasets over a WAN. Searches for WAN costs, transmission delay, and privacy leakage found no passage addressing the claim. (LLM, conf=0.75)
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Could not verify
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“the physical proximity between the computing and information-generation sources promises several benefits compared to the traditional cloud-based computing paradigm, including low latency, energy efficiency, privacy protection, reduced bandwidth consumption, on-premises, and context awareness [6], [8].”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > I. I N T R O D U C T I O N
What the sources say
- Not checked — no full text of the sourcecites [6] 6. W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, "Edge computing: Vision and challenges," IEEE Internet Things J., vol. 3, no. 5, pp. 637-646, Oct. 2016. source
- Supportedcites [8] 8. Y. Mao, C. You, J. Zhang, K. Huang, and K. B. Letaief, "A survey on mobile edge computing: The communication perspective," IEEE Commun. Surveys Tuts., vol. 19, no. 4, pp. 2322-2358, 4th Quart., 2017. source
The comparison in “Mobile Edge Computing Versus Mobile Cloud Computing” (p. 3) identifies lower latency, mobile-device energy savings, context awareness, and improved privacy and security as MEC advantages. “Mobile Computing for 5G: From Clouds to Edges” (p. 1) explains that moving traffic toward the edge avoids burdening backhaul networks, while the privacy discussion (p. 3) gives enterprise-managed deployment as an example of keeping data on premises. (LLM, conf=0.88)
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“A good performance improvement is obtained by transferring knowledge from both the intermediate layers and last layer of the teacher to a shallower student while other architectures and transfer techniques do not fare so well and some of them even lead to negative performance impact.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
What the sources say
- Not checked — no full text of the sourcecites [62] 62. R. Sharma, S. Biookaghazadeh, B. Li, and M. Zhao, "Are existing knowledge transfer techniques effective for deep learning with edge devices?" in Proc. IEEE Int. Conf. Edge Comput. (EDGE), Jul. 2018, pp. 42-49. source
- Could not verifycites [44] 44. Q. Chen, Z. Zheng, C. Hu, D. Wang, and F. Liu, "Data-driven task allocation for multi-task transfer learning on the edge," in Proc. IEEE 39th Int. Conf. Distrib. Comput. Syst. (ICDCS), 2019. sourceExperimental — accuracy not yet measured
Split into 2 atoms — 0 confirmed, 0 partially supported, 0 disputed, 0 misattributed, 2 unverifiable. Expand the claim to see per-atom verdicts.
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
Every source the paper cites for this claim was checked and supports it.
In the paper
“The early work on random gossip algorithms is gossip averaging [63], which can fast converge toward a consensus among nodes by exchanging information peer to peer.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
What the sources say
- Supportedcites [63] 63. S. Boyd, A. Ghosh, B. Prabhakar, and D. Shah, "Randomized gossip algorithms," IEEE Trans. Inf. Theory, vol. 52, no. 6, pp. 2508-2530, Jun. 2006. source
The paper describes gossip averaging as nodes communicating with randomly chosen neighbors (Randomized Gossip Algorithms, p. 1). It studies convergence to the vector of averages and the design of the fastest gossip algorithm (Previous Results, p. 3; Randomized Gossip Algorithms, p. 1), supporting the peer-to-peer consensus paraphrase. (LLM, conf=0.89)
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Supported
In the paper
“The algorithm is based on the convergence analysis of distributed gradient descent and can be applied to federated learning in edge computing with provable convergence.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 2) Aggregation Frequency Control:
What the sources say
- Not matchedcites [51] 51. S. Wang et al., "Adaptive federated learning in resource constrained edge computing systems," IEEE J. Sel. Areas Commun., vol. 37, no. 3, pp. 1205-1221, Jun. 2019.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As a result, the transmission latency of data offloading decreases, the data privacy increases, and the WAN bandwidth cost reduces.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 5) Level 4-Cloud-Edge Cotraining and Inference: Train-
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The main challenges of federated learning are optimization and communication.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > C. Enabling Technologies
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While edge computing and AI complement each other from a technical perspective, their application and popularization are also mutually beneficial.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 2) Edge Computing Is Able to Prosper AI With Richer Data and Application Scenarios:
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Though the federated learning technique exploits a new decentralized deep learning architecture, it is built upon a central server for aggregating local updates.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > C. Enabling Technologies
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“As forecast by Gartner [33], more than 80% of enterprise IoT projects will include an AI component by 2022, up from only 10% today.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > A. Motivation and Benefits of Edge Intelligence
What the sources say
- Not matchedcites [33] 33. AI Trends for Enterprise Computing. [Online]. Available: https://www.gartner.com/ smarterwithgartner/3-ai-trends-for-enterprise- computing/
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This conflict indicates that there is no”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 5) Level 4-Cloud-Edge Cotraining and Inference: Train-
Load-bearingStrength:hedged· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Energy efficiency is mainly affected by the size of the target training model and resources of the used devices.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 6) Energy Efficiency:
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“ResNet [20], the state-of-the-art effort, uses the”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Convolution Neural Network:
What the sources say
- Not checked — no full text of the sourcecites [20] 20. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proc. IEEE CVPR, Jun. 2016, pp. 770-778. source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“real-time video analytics is envisioned to be a killer application for edge computing [12], [37], [38].”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) Edge Computing Can Be Popularized With AI Applications:
What the sources say
- Not checked — no full text of the sourcecites [12] 12. G. Ananthanarayanan et al., "Real-time video analytics: The killer app for edge computing," Computer, vol. 50, no. 10, pp. 58-67, 2017. source
- Not checked — no full text of the sourcecites [37] 37. H. Zhang, G. Ananthanarayanan, P. Bodik, M. Philipose, P. Bahl, and M. J. Freedman, "Live video analytics at scale with approximation and delay-tolerance," in Proc. USENIX NSDI, 2017, pp. 377-392.
- Not checked — no full text of the sourcecites [38] 38. C.-C. Hung et al., "VideoEdge: Processing camera streams using hierarchical clusters," in Proc. IEEE/ACM Symp. Edge Comput. (SEC), Oct. 2018, pp. 115-131. source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“AlexNet requires 61 million weights and 724 million MACs (multiply-add computation) to classify the image with a size of 227 × 227.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Convolution Neural Network:
What the sources say
- Not matchedcites [18] 18. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," in Proc. NIPS, 2012, pp. 1097-1105.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
In the paper
“However, Gaia focuses on geodistributed datacenters that are capacity-unlimited, making it is not generally applicable to edge computing nodes whose capacity is highly constrained.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 2) Aggregation Frequency Control:
What the sources say
- Not matchedcites [50] 50. K. Hsieh, A. Harlap, N. Vijaykumar, D. Konomis, G. R. Ganger, and P. B. Gibbons, "Gaia: Geo-distributed machine learning approaching LAN speeds," in Proc. NSDI, 2017, pp. 629-647.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Under the decentralized training mode, the convergence value depends on the way the gradient is synchronized and updated.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 2) Convergence:
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“When training the DNN model by using the data originated at a massive of end devices, the raw data or intermediate data should be transferred out of the end devices.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 3) Privacy:
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Deep learning represents the state-of-the-art AI technology as well as a highly resource-demanding workload that naturally suits for edge computing.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > B. Deep Learning and Deep Neural Networks
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes? Based: unclearIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“When training the DNN model in a decentralized manner, both the computation and communication processes consume enormous energy.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 6) Energy Efficiency:
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
- Rests on an assumption: For most end devices, they are energy-constrained.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, this is achieved at the cost of increased computational latency and energy consumption.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 5) Level 4-Cloud-Edge Cotraining and Inference: Train-
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“GoogleNet achieves a better accuracy performance than VGG-16, while only requiring seven million weights and 1.43G MACs to process the image with the same size.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Convolution Neural Network:
What the sources say
- Not checked — no full text of the sourcecites [28] 28. C. Szegedy et al., "Going deeper with convolutions," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2015, pp. 1-9. source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
In the paper
“MeDNN improves the DNN model inference by 1.86-2.44×with two to four worker nodes and saves 26.5% of additional computing time and 14.2% of extra communication time.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Model Compression:
What the sources say
- Not checked — no full text of the sourcecites [84] 84. J. Mao et al., "MeDNN: A distributed mobile system with enhanced partition and deployment for large-scale DNNs," in Proc. 36th Int. Conf. Comput.-Aided Design, Nov. 2017, pp. 751-756. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Communication overhead is affected by the size of the original input data, the way of transmission, and the available bandwidth.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > VII. C O N C L U S I O N
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Due to the combinatorial nature, the high-dimensional configuration problem involves a huge search space of parameters and is very challenging to tackle.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > D. Summary of Existing Systems and Frameworks
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Rests on an assumption: Standard performance indicators such as top-k accuracy or mean average precision fail to reflect the runtime performance of DNN model inference on edge devices.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, data parallelism may bring heavy overhead of communication, while model parallelism usually leads to severe underutilization of computation resources.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes? Based: unclearIt may state two separate claims as one.
In the paper
“PipeDream shows the advantage of reducing communication overhead and utilizing computing resource efficiently.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
What the sources say
- Not checked — no full text of the sourcecites [61] 61. A. Harlap, D. Narayanan, A. Phanishayee, V. Seshadri, G. R. Ganger, and P. B. Gibbons, "PipeDream: Fast and efficient pipeline parallel DNN training," 2018, arXiv:1806.03377. [Online]. Available: https://arxiv.org/abs/1806.03377 source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The communication latency may vary from the size of transmitted raw or intermediate data and the bandwidth of network connection.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > VII. C O N C L U S I O N
Strength:hedged· not yet calibratedCausal:conditional· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“By deployment on large-scale systems, Daily et al. [66] show that the trivial gossip-based algorithms at scale lead to a communication imbalance, poor convergence, and heavy communication overhead.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
What the sources say
- Not checked — no full text of the sourcecites [66] 66. J. Daily, A. Vishnu, C. Siegel, T. Warfel, and V. Amatya, "GossipGraD: Scalable deep learning using gossip communication based asynchronous gradient descent," 2018, arXiv:1803.05880. [Online]. Available: https://arxiv.org/ abs/1803.05880 source
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“FoggyCache reduces computation latency and energy consumption by a factor of 3× to 10×.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) Edge Caching:
What the sources say
- Not checked — no full text of the sourcecites [95] 95. P. Guo, B. Hu, R. Li, and W. Hu, "FoggyCache: Cross-device approximate computation reuse," in Proc. ACM Mobicom, 2018, pp. 19-34. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Arguably, latency is one of the most fundamental performance indicators of distributed DNN model training since it directly influences when the trained model is available for use.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > VII. C O N C L U S I O N
Strength:hedged· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This is based on the important observation that a DNN model can be split inside between two successive layers with two partitions deployed on different locations without losing accuracy.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably not a substantial claim. The paper may give no reason why it holds.
In the paper
“the proposed automatic optimization framework AdaDeep [75] systematically formulates the goals and constraints on accuracy, latency, storage, and energy into a unified optimization problem and leverages DRL to effectively find a good combination of compression techniques.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Model Compression:
What the sources say
- Not checked — no full text of the sourcecites [75] 75. S. Liu, Y. Lin, Z. Zhou, K. Nan, H. Liu, and J. Du, "On-demand deep model compression for mobile devices: A usage-driven model selection framework," in Proc. 16th Annu. Int. Conf. Mobile Syst., Appl., Services, 2018, pp. 389-400. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The decentralized architecture is naturally friendly to user's privacy, for which the systems that are based on the decentralized architecture such as BlockFL and GossipGraD typically preserve privacy better.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > Table 2 Overview of Systems and Frameworks on EI Model Training
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Intuitively, this communication overhead increases the training latency, energy, and bandwidth consumption.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > VII. C O N C L U S I O N
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“Precog uses predictions of Markov chains to prefetch data onto the mobile device and reach a speedup of 5×.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) Edge Caching:
What the sources say
- Not checked — no full text of the sourcecites [94] 94. U. Drolia, K. Guo, and P . Narasimhan, "Precog: Prefetching for image recognition applications at the edge," in Proc. ACM/IEEE Symp. Edge Comput. (SEC), Oct. 2017, p. 17. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Compared with the DNN training under the cloud-based framework, the DNN training under edge-based framework pays more attention to protecting users' privacy and training an available deep learning model faster.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > Table 2 Overview of Systems and Frameworks on EI Model Training
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The latency of the distributed training process typically consists of the computation latency and the communication latency.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > VII. C O N C L U S I O N
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“Both Blot et al. [64] and Jin et al. [65] apply gossip algorithms on the updates of SGD, but neither of them has performance convergence degradation at large scale.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
What the sources say
- Not checked — no full text of the sourcecites [64] 64. M. Blot, D. Picard, M. Cord, and N. Thome, "Gossip training for deep learning," 2016, arXiv:1611.09726. [Online]. Available: https://arxiv.org/abs/1611.09726 source
- Not checked — no full text of the sourcecites [65] 65. P. H. Jin, Q. Yuan, F. Iandola, and K. Keutzer, "How to scale distributed deep learning?" 2016, arXiv:1611.04581. [Online]. Available: https://arxiv.org/abs/1611.04581 source
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
In the paper
“ReXCam reduces computation workload by 4.6× and improves DNN model inference accuracy by 27%.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 5) Input Filtering:
What the sources say
- Not checked — no full text of the sourcecites [99] 99. S. Jain, J. Jiang, Y. Shu, G. Ananthanarayanan, and J. Gonzalez, "ReXCam: Resource-efficient, cross-camera video analytics at enterprise scale," 2018, arXiv:1811.01268. [Online]. Available: https://arxiv.org/abs/1811.01268 source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“For the object recognition application, Huang et al. [120] investigate the influence of the main factors, e.g., number of proposals, input image size, and the selection of feature extractor, on inference speed and accuracy.Based on their experiment results, a new combination of these factors is found to outperform the state-of-the-art method.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > D. Tradeoff Design With Various DNN Performance Metrics
What the sources say
- Not checked — no full text of the sourcecites [120] 120. J. Huang et al., "Speed/accuracy trade-offs for modern convolutional object detectors," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 7310-7311. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Rests on an assumption: Standard performance indicators such as top-k accuracy or mean average precision fail to reflect the runtime performance of DNN model inference on edge devices.
In the paper
“Compared to the approach that uploads the entire model, IONN significantly improves query performance and energy consumption during DNN model uploading.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 1) Model Compression:
What the sources say
- Not checked — no full text of the sourcecites [82] 82. H.-J. Jeong, H.-J. Lee, C. H. Shin, and S.-M. Moon, "IONN: Incremental offloading of neural network computations from mobile devices to edge servers," in Proc. ACM Symp. Cloud Comput., 2018, pp. 401-411. source
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The gossip distributed algorithms enjoy the advantage of full asynchronization and total decentralization as they have no requirement on centralized nodes or variables.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“the cascading network [91] simply adds the MP layer and fully connected layer to the standard DNN model and achieves a speedup of 20%.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > The aggregation methods work when multiple mobile
What the sources say
- Not checked — no full text of the sourcecites [91] 91. S. Leroux et al., "The cascading neural network: Building the Internet of smart things," Knowl. Inf. Syst., vol. 52, no. 3, pp. 791-814, 2017.
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This process will tend to work if the features are general (i.e., suitable to both base and target tasks) instead of specific to the base task.”
§ Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing This article conducts a comprehensive survey of the research efforts on edge intelligence. It provides an overview of the architectures, frameworks, and emerging key > 4) DNN Splitting:
Strength:hedged· not yet calibratedCausal:conditional· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper relies on this without support.
There is a lack of a dedicated venue for summarizing, discussing, and disseminating recent advances of edge intelligence in both industry and academia.
“There is, in general, a lack of venue dedicated for summarizing, discussing, and disseminating the recent advances of EI, in both industrial and academia.”
The paper relies on this without support.
Research and practice on edge intelligence are still in a very early stage.
“Notably, research and practice on this emerging interdiscipline-EI-are still in a very early stage.”
The paper relies on this without support.
The edge ecosystem will present many novel application scenarios for AI and fuel the continuous booming of AI.
“Clearly, via bringing the huge volumes of data to AI, the edge ecosystem will present many novel application scenarios for AI and fuel the continuous booming of AI.”
The paper relies on this without support.
For most end devices, they are energy-constrained.
“However, for most end devices, they are energy-constrained.”
The paper relies on this without support.
It is inevitable to deal with privacy issues when raw or intermediate data are transferred out of end devices.
“Obviously, it is inevitable to deal with privacy issues in this scenario.”
The paper relies on this without support.
For some real-time intelligent mobile applications, they usually have stringent deadline requirement such as 100-ms latency.
“For some real-time intelligent mobile applications (e.g., AR/VR mobile gaming and intelligent robots), they usually have stringent deadline requirement such as 100-ms latency.”
The paper relies on this without support.
For some mobile applications requiring high reliability, they demand ultrahigh accuracy on DNN model inference.
“For some mobile applications requiring a high level of reliability, such as self-driving car and face authentication, they demand the ultrahigh accuracy on the DNN model inference.”
The paper relies on this without support.
Most existing efforts use a single compression technique.
“While most existing efforts use a single compression technique, they may not suffice to meet the diverse requirements and constraints on accuracy, latency, storage, and energy imposed by some IoT devices.”
The paper relies on this without support.
Standard performance indicators such as top-k accuracy or mean average precision fail to reflect the runtime performance of DNN model inference on edge devices.
“However, it is difficult for software developers to choose an appropriate DNN model for the EI application because the standard performance indicators such as top-k accuracy or mean average precision fail to reflect the runtime performance of DNN model inference on edge devices.”
The paper relies on this without support.
Most current edge AI programming/software platforms mainly serve as relays for connecting to cloud data centers.
“Nevertheless, currently, most of these platforms mainly serve as relays for connecting to the powerful cloud data centers.”
The paper relies on this without support.
Most deep learning-based AI models are highly resource-intensive.
“Most of the deep learning-based AI models are highly resourceintensive, which means that powerful computing capability supported by abundant hardware resources (e.g., GPU, field-programmable gate array (FPGA), and TPU) is important to boost the performance of these AI models.”
The paper relies on this without support.
For an EI application with a specific mission, there is usually a series of DNN model candidates that are capable of finishing the task.
“For an EI application with a specific mission, there is usually a series of DNN model candidates that are capable of finishing the task.”
The paper relies on this without support.
The service environments for many EI application scenarios are of high dynamics and it is hard to accurately predict future events.
“Since for many EI application scenarios (e.g., smart cities), the service environments are of high dynamics and it is hard to accurately predict future events.”
The paper relies on this without support.
The high-efficiency operation of EI services may require close collaboration and integration across different service providers.
“The high-efficiency operation of EI services may require close collaboration and integration across different service providers, e.g., for implementing expanded resource sharing and smooth service handover.”
The paper relies on this without support.
A user can be a service consumer and, meanwhile, a data generator as well.
“Also, for EI service, a user can be a service consumer and, meanwhile, a data generator as well.”
The paper relies on this without support.
There is a stringent need to push the AI frontier from the cloud to the network edge.
“Driving by flourishing of both AI and IoT, there is a stringent need to pushing the AI frontier from the cloud to the network edge.”
The paper relies on this without support.
Edge computing is widely recognized as a promising solution to support computation-intensive AI applications in resource-constrained environments.
“To fulfill this trend, edge computing has been widely recognized as a promising solution to support computation-intensive AI applications in resource-constrained environments.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Additionally, UAVs generate lots of data at the network edge and directly sharing original data sets between many edge nodes has a high risk associated with it [8].”
From A Survey on the Convergence of Edge Computing and AI for UAVs: Opportunities and Challenges (2022) · cites this paper as [8]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Edge Intelligence (EI) Zhou et al. (2019) proposes a new paradigm combining AI and edge computing, with the goal of performing distributed computing of DL models.”
From Deepfakes: current and future trends (2024) · cites this paper as Zhou et al. 2019
The cited source says what the claim attributes to it.
In the citing paper
“This entails some advantages such as low latency, energy and bandwidth efficiency, privacy protection, and context awareness (Zhou et al. 2019).”
From Deepfakes: current and future trends (2024) · cites this paper as Zhou et al. 2019
The cited source says what the claim attributes to it.
In the citing paper
“In the case of training a deep learning model in an edge computing environment, where distributed models are trained locally first and then updates are aggregated centrally (e.g., federated learning), the control of updates aggregation frequency has a significant influence on the communication overhead.”
From A Survey on the Convergence of Edge Computing and AI for UAVs: Opportunities and Challenges (2022) · cites this paper as [8]
In the citing paper
“Edge AI provides a promising solution for connected intelligence by enabling data collection, processing, transmission, and consumption at the network edge [29], [30].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [30]
In the citing paper
“All of these reviews only have a small fraction to discuss the edge DNN design which is the key element of edge intelligence systems.”
From Bringing ai to edge: from deep learning’s perspective (2022) · cites this paper as [13]
In the citing paper
“Smart city [113] is another important application scenario for deep-learning-enabled edge computing.”
From Deep learning for edge computing applications: A State-of-the-Art survey (2020) · cites this paper as [113]
In the citing paper
“In the current scenario, Blockchain provides a high degree of privacy for health data [49].”
From 6G Communication Technology: A Vision on Intelligent Healthcare (2021) · cites this paper as [49]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Inference metrics are counted as five but six are listed
MinorThe section introduces five inference metrics, but its numbered list runs from latency through memory footprint and contains six.
“To describe the service quality of the EI model inference, we introduce the following five metrics.”
“## 6) Memory Footprint:”
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 5×
“GoogleNet achieves a better accuracy performance than VGG-16, while only requiring seven million weights and 1.43G MACs to process the image with the same size.”
BackgroundMethodInfluentialImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 7×
“This is because for DNNs as exemplified by AlexNet, the energy of the convolutional layers dominates the total energy cost, while the number in the fully connected layers contributes most of the total number of weights in the DNN.”
BackgroundMethodInfluentialHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 4×
“4, each neuron in LSTM is called memory cell and includes a multiplicative forget gate, input gate, and output gate.”
BackgroundInfluentialLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562 · cited 2×
“GoogleNet achieves a better accuracy performance than VGG-16, while only requiring seven million weights and 1.43G MACs to process the image with the same size.”
MethodLearning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892 · cited 1×
“Leveraging the backpropagation mechanism [26], [27], the error rate is propagated back across the whole neural network, and the weights are updated based on the gradient and the learning rate.”
(2016) · Cited by 31,590
Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357 · cited 2×
“[32] V.”
Flagged first, then by citations
28 of the 168 references couldn’t be matched to a known paper.
Research works printed but not linked: 11
- 0, 3 AI Trends for Enterprise Computing
- 0, Microsoft Interactive Cloud Gaming
- 0, Democratizing AI
- hsieh, 2017, Gaia: Geo-distributed machine learning approaching LAN speeds, Proc NSDI, 629
- 2018, 5 Trends Emerge in the Gartner Hype Cycle for Emerging Technologies
- 0, Cisco global cloud index Forecast and methodology 2016–2021
- 0, Accelerating AI on the Intelligent Edge
- 2017, IEC White Paper Edge Intelligence
- 0, Edge Intelligence for Industrial Internet of Things
- han, 2015, Learning both weights and connections for efficient neural network, Proc Adv Neural Inf Process Syst, 1135
- 2018, 5 Trends Emerge in the Gartner Hype Cycle for Emerging Technologies
Cited by
Sorted by citations
Items 901–1,000 of 2,413
Construction Jobsite Image Classification Using an Edge Computing Framework
Chen, G., Alsharef, A. F., & Jaselskis, E. J. (2024) · Sensors · doi:10.3390/s24206603 · Cited by 14
“This complies with level 4 edge intelligence (EI), according to Zhou et al. [26] They identi fi ed a six-level rating for EI, with Level 6 representing scenarios where both training and inference occur entirely on the device, and Level 1 is all on the cloud.”
BackgroundMethodInfluentialZhao, S., Tongtong, L., Jin, H., & Yao, D. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3562721 · Cited by 12
Smaller, Smarter, Closer: The Edge of Collaborative Generative Artificial Intelligence
Morabito, R., & Jang, S. Y. (2025) · IEEE Internet Computing · doi:10.1109/mic.2025.3575493 · Cited by 11
“19 As demand rises, edge devices can quickly reach capacity limits, making cloud-based GenAI a necessary complement, particularly when edge resources saturate.”
Reduced-Order Neural Network Synthesis With Robustness Guarantees
Drummond, R., Turner, M. C., & Duncan, S. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3182893 · Cited by 11
Energy-efficient Collaborative Sensing: Learning the Latent Correlations of Heterogeneous Sensors
Liang, Y., Wang, X., Yu, Z., Guo, B., Zheng, X., & Samtani, S. (2021) · ACM Transactions on Sensor Networks · doi:10.1145/3448416 · Cited by 10
“In addition, edge computing is shedding lights on mobile devices oriented deep learning [8, 70].”
BackgroundBin, K., Lin, J., Tong, X., et al. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3108467 · Cited by 10
“With the maturity of edge computing devices [35], CO-SDL is very likely to be pushed to the edge of the Internet of things, thus achieving large-scale on-site computing and edge intelligence [36].”
BackgroundMa, F., Wang, B., Li, M., et al. (2021) · Frontiers in Energy Research · doi:10.3389/fenrg.2021.754335 · Cited by 10
“Therefore, the research on the intelligent identi fi cation method of front-end edge intelligent icing monitoring equipment has become the inevitable development trend of online icing monitoring (Chen et al., 2019; Zhou et al., 2019).”
BackgroundAn Adaptive Task Migration Scheduling Approach for Edge‐Cloud Collaborative Inference
Zhang, B., Li, Y., Zhang, S., et al. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/8804530 · Cited by 10
“Edge devices deployed generally have some constraints including energy and computational capacity [3].”
BackgroundRealizing contact-less applications with Multi-Access Edge Computing
Ranaweera, P. S., de Alwis, C., Jurcut, A. D., & Liyanage, M. (2022) · ICT Express · doi:10.1016/j.icte.2022.03.001 · Cited by 10
Dynamic Path Based DNN Synergistic Inference Acceleration in Edge Computing Environment
Meng, Z., Zhou, B., Wang, H., Dong, F., & Zhao, W. (2021) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads53394.2021.00076 · Cited by 10
Liu, W., He, W., Hu, B., & Chang, C.-H. (2022) · IEEE International System-on-Chip Conference (SOCC) · doi:10.1109/socc56010.2022.9908112 · Cited by 11
“Nevertheless, camera-based attacks pose a real threat with the current trend of combining artificial intelligence (AI) with edge computing [15] to analyze raw visual data locally.”
BackgroundOperational State Recognition of a DC Motor Using Edge Artificial Intelligence
Strantzalis, K., Gioulekas, F., Katsaros, P., et al. (2022) · Sensors · doi:10.3390/s22249658 · Cited by 10
“Therefore, edge computing is an important avenue in the evolution of AI and its applicability to predictive maintenance [2].”
BackgroundLearning-Based Query Scheduling and Resource Allocation for Low-Latency Mobile-Edge Video Analytics
Lin, J., Yang, P., Wu, W. R., Zhang, N., Han, T., & Yu, L. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3300696 · Cited by 11
“Since mobile-edge nodes are only one-hop away from cameras [15], they can help to enable low latency [16].”
BackgroundTongueMobile: automated tongue segmentation and diagnosis on smartphones
Huang, Z.-H., Huang, W., Wu, H.-C., et al. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08902-5 · Cited by 10
Niu, X., Huang, Y., Wang, Z., et al. (2024) · IEEE Transactions on Computers · doi:10.1109/tc.2024.3354033 · Cited by 10
“Under this tendency, the combination of AI and edge computing is inevitable, which has also led to a new cross-research, namely edge intelligence (EI) [7].”
BackgroundResearch and Application of Edge Computing Based on Deep Learning
Cui, W. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1646/1/012016 · Cited by 10
Zhang, S., Wang, J., Tong, J., et al. (2020) · IEEE Access · doi:10.1109/access.2020.3037172 · Cited by 10
“In addition, the fusion of edge and cloud computing makes it possible to use machine learning techniques on edge networks for edge intelligence [6].”
BackgroundSelf-citationA Survey on Edge Computing in Bioinformatics and Health Informatics
Tsai, Y.-T., & Lin, Z. Y. (2020) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm49941.2020.9313103 · Cited by 10
“More recently, edge computing capable with artificial intelligence technologies has received much attention in the research literature [16].”
BackgroundCareEdge: A Lightweight Edge Intelligence Framework for ECG-Based Heartbeat Detection
Zhen, P., Han, Y., Dong, A., & Yu, J. (2021) · Procedia Computer Science · doi:10.1016/j.procs.2021.04.070 · Cited by 10
Memory-aware Efficient Deep Learning Mechanism for IoT Devices
Banerjee, J., Islam, S., Wei, W., Chen, P., Zhu, D. K., & Xie, M. (2021) · IEEE International Conference on Application-specific Systems, Architectures and Processors (ASAP) · doi:10.1109/asap52443.2021.00035 · Cited by 11
Mobile Edge Computing for Content Distribution and Mobility Support in Smart Cities
do Prado, P. F., Peixoto, M. L. M., Araújo, M. C., Gama, E. S., Gonçalves, D. M., Silva, M. V. S., Immich, R., Madeira, E. R. M., & Bittencourt, L. F. (2021) · Springer eBooks · doi:10.1007/978-3-030-69893-5_19 · Cited by 10
Effective Goal-oriented 6G Communications: the Energy-aware Edge Inferencing Case
Merluzzi, M., Filippou, M. C., Baltar, L. G., & Strinati, E. C. (2022) · Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit) · doi:10.1109/eucnc/6gsummit54941.2022.9815737 · Cited by 10
“Related work: Edge inference has recently gained considerable attention [6], [8].”
BackgroundLightweight Group Authentication for Decentralized Edge Collaboration
Fang, H., Wang, X., Tomasin, S., et al. (2022) · IEEE Communications Magazine · doi:10.1109/mcom.004.2200264 · Cited by 10
“…Wang is with considered to be one of the key missing components in 5G networks and is widely recognized to one of the essential functions for 6G systems [1]. leveraging machine learning (ML) and available computing resources at the network edge, each edge node can proactively carry out…”
BackgroundMobile App Usage Patterns Aware Smart Data Pricing
Yin, J., Fan, Y., Tong, X., et al. (2020) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2020.2971896 · Cited by 10
“Zhou et al. [29] proposed an artificial intelligence (AI) based method to build up user behaviors model at the network edge, which can help ISPs improve the efficiency significantly and create new business models especially in Internet of Things (IoT).”
MethodSelf-citationRunning Efficiently CNNs on the Edge Thanks to Hybrid SRAM-RRAM In-Memory Computing
Rios, M. A., Ponzina, F., Ansaloni, G., Levisse, A., & Atienza, D. (2021) · Design, Automation, and Test in Europe · doi:10.23919/date51398.2021.9474233 · Cited by 11
“Edge Intelligence is predicted to parallel this success by enabling AI applications on smart Internet-of-things (IoT) devices, paving the way for novel solutions in many exciting domains, such as, enhanced reality and personalized assistance [1].”
BackgroundJoint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated LearningPreprint
Shi, W., Zhou, S., Niu, Z., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.07174 · Cited by 10
“Therefore, the model accuracy within certain training time budgets (i.e., convergence rate w.r.t. time ), which is critical for latency constrained FL applications [27], [28], has not been addressed yet.”
BackgroundCui, S., FU, Y., Fu, H. Y., & Shen, W. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.104300 · Cited by 16
Energy-Efficient Classification at the Wireless Edge with Reliability Guarantees
Merluzzi, M., Battiloro, C., Lorenzo, P. D., et al. (2022) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops53468.2022.9814659 · Cited by 9
“As pointed out in [1], [4], several aspects must be tackled when performing edge inference tasks in the most efficient way, such as model compression techniques to reduce the memory footprint [5], model selection strategies to adaptively select the inference model online [6], or application oriented optimization, for…”
Tailoring FANET-Based 6G Network Slices in Remote Areas for Low-Latency Applications
Grasso, C., Raftopoulos, R., & Schembra, G. (2022) · IFIP Networking Conference (IFIP Networking) · doi:10.23919/ifipnetworking55013.2022.9829809 · Cited by 9
“Edge Intelligence [5][6], powered by AI techniques, is considered one of the key missing elements in 5G networks, and will represent a key enabler for future 6G networks.”
Vitelli, M., Cerro, G., Gerevini, L., Miele, G., Ria, A., & Molinara, M. (2023) · Computers · doi:10.3390/computers12020023 · Cited by 11
Bilateral Improvement in Local Personalization and Global Generalization in Federated Learning
Wang, Y., Xu, H., Ali, W., Zhou, X., & Shao, J. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3399074 · Cited by 10
Peer-to-Peer Federated Learning on Software-Defined Optical Access Network
Pakpahan, A. F., & Hwang, I. (2024) · IEEE Access · doi:10.1109/access.2024.3411639 · Cited by 9
“Edge computing involves direct data processing on edge devices like smartphones or IoT sensors, enhancing efficiency and reducing latency [3], [6], [7].”
BackgroundEnergy Efficient FPGA-Based Binary Transformer Accelerator for Edge Devices
Du, C., Ko, S., & Zhang, H. (2024) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas58744.2024.10558631 · Cited by 13
“With the remarkable performance, transformer models are also desired to be deployed at the edge to improve the quality of services for many applications [9].”
BackgroundPrivate Collaborative Edge Inference via Over-the-Air Computation
Yilmaz, S. F., Hasırcıoglu, B., Qiao, L., & Gündüz, D. (2025) · IEEE Transactions on Machine Learning in Communications and Networking · doi:10.1109/tmlcn.2025.3526551 · Cited by 9
“In a collaborative system, client participation depends on the privacy, security, energy and utility requirements [30], [31].”
Li, X., Sun, S., Liu, M., Ren, J., Jiang, X., & He, T. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3466208 · Cited by 9
Human-Centered Edge AI and Wearable Technology for Workplace Health and Safety in Industry 5.0
Nguyen, T., Nguyen, D. H., Nguyen, T., Tran, K. D., & Tran, K. P. (2024) · Springer series in reliability engineering · doi:10.1007/978-3-031-71495-5_8 · Cited by 9
Integrated sensing and communications waveform design: Fundamentals, applications, challenges
Luo, Z., & Wang, Z. (2024) · Physical Communication · doi:10.1016/j.phycom.2024.102532 · Cited by 9
Chen, Z., Hoang, D., Piran, F. J., Chen, R., & Imani, F. (2025) · Internet of Things · doi:10.1016/j.iot.2025.101568 · Cited by 10
Interference Mitigation Strategies in Beyond 5G Wireless Systems: A Review
Alzubaidi, O. T. H., Alheejawi, S., Hindia, M. N., et al. (2025) · Electronics · doi:10.3390/electronics14112237 · Cited by 9
Benatti, S., Donati, E., Moin, A., Zanghieri, M., Orlandi, M., Burrello, A., Artoni, F., Micera, S., Benini, L., & Rabaey, J. M. (2025) · Proceedings of the IEEE · doi:10.1109/jproc.2025.3581995 · Cited by 10
“2) DL Approaches: DL architectures [150], [151] can capture spatial and temporal information of an input signal (e.g., convolutional neural networks (CNNs) and temporal convolutional networks (TCNs)), as well as to exploit the sequential nature of the data (e.g., recurrent neural networks (RNNs)…”
A Systematic Review for Ammonia Monitoring Systems Based on the Internet of Things
da Silva, A. H. M. C., da Silva, M. K., Santos, A., et al. (2025) · IoT · doi:10.3390/iot6040066 · Cited by 9
Silva, M., Teles, A. S., Lopes, R., et al. (2020) · Mobile Networks and Applications · doi:10.1007/s11036-020-01630-3 · Cited by 9
“Thus, AI techniques can be embedded in the gateway to generate knowledge [46, 48].”
BackgroundiCOS: A Deep Reinforcement Learning Scheme for Wireless-Charged MEC Networks
Wan, C., Guo, S., He, J., Liu, G., & Zhou, P. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3166973 · Cited by 9
Reliable DNN Partitioning for UAV Swarm
Zhao, M., Zhang, X., Meng, Z., et al. (2022) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc55113.2022.9824945 · Cited by 9
Yang, Y.-T. C., & Wei, H. (2022) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2022.3220521 · Cited by 9
Huang, Z., Dong, F., Shen, D., Wang, H., Guo, X., & Fu, S. (2022) · Proceedings of the International Conference on Parallel Processing · doi:10.1145/3545008.3545071 · Cited by 9
A Joint Framework to Privacy-Preserving Edge Intelligence in Vehicular Networks
Firdaus, M., & Rhee, K.-H. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-25659-2_12 · Cited by 10
Li, H., Wang, X., Liu, Y., Liu, G., Zhai, Z., Yan, X., Wang, H., & Zhang, Y. (2023) · Sustainability · doi:10.3390/su151410783 · Cited by 9
BIRP: Batch-aware Inference Workload Redistribution and Parallel Scheme for Edge Collaboration
Sun, H., Chen, X., Qian, Z., Li, Z., Chen, N., Cao, T., Xu, S., & Zhou, Y.-T. (2023) · Proceedings of the International Conference on Parallel Processing · doi:10.1145/3605573.3605615 · Cited by 9
Self-citationEmpowered edge intelligent aquaculture with lightweight Kubernetes and GPU-embedded
Fathoni, H., Yang, C., Huang, C., et al. (2024) · Wireless Networks · doi:10.1007/s11276-023-03592-2 · Cited by 9
“The edge computing architecture consists of three layers (user plane, edge plane, and cloud plane) [8].”
Hong, Z., Lin, Q., & Hu, B. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3376579 · Cited by 12
“Driving by this trend, cloud computing, an emerging paradigm that promotes pre-training tasks from the roadside perception to the edge-cloud planning has been widely recognized as a promising solution [11].”
Background6G: Enabling the Future of Healthcare Delivery
Karak, A., Chirputkar, A., & Ashok, P. (2024) · IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems (ICITEICS) · doi:10.1109/iciteics61368.2024.10625060 · Cited by 10
ERP and Artificial Intelligence based Smart Financial Information System Data Analysis Framework
Dong, A. (2021) · International Conference on Inventive Computation Technologies (ICICT) · doi:10.1109/icict50816.2021.9358659 · Cited by 9
“Financial information technology has greatly improved the flexibility of financial processing and improved the efficiency of the company [20-22].”
Backgroundperf4sight: A toolflow to model CNN training performance on Edge GPUs
Rajagopal, A., & Bouganis, C.-S. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00112 · Cited by 11
“Consequently, there has been a push to increase the intelligence of the processing performed on edge devices [26].”
BackgroundDeep learning in multiagent systems
Esterle, L. (2022) · Elsevier eBooks · doi:10.1016/b978-0-32-385787-1.00022-1 · Cited by 9
Online Performance and Power Prediction for Edge TPU via Comprehensive Characterization
Ni, Y., Kim, Y., Rosing, T., et al. (2022) · Design, Automation, and Test in Europe · doi:10.23919/date54114.2022.9774764 · Cited by 9
Slicing a FANET for heterogeneous delay-constrained applications
Grasso, C., Raftopoulos, R., & Schembra, G. (2022) · Computer Communications · doi:10.1016/j.comcom.2022.08.024 · Cited by 9
Liu, L., Zhao, Y., Qi, F., Zhou, F., Xie, W., He, H., & Zheng, H. (2022) · Electronics · doi:10.3390/electronics11213641 · Cited by 9
Liu, C., Yang, H., Ke, R., Sun, W., Wang, J., & Wang, Y. (2023) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981231160174 · Cited by 9
“Estimates suggest that all data centers globally can only handle approximately 20ZB, while approximately 850ZB were generated daily in 2021 (7).”
BackgroundA Cloud-Edge Artificial Intelligence Framework for Sensor Networks
Loseto, G., Scioscia, F., Ruta, M., et al. (2023) · International Workshop on Advances in Sensors and Interfaces (IWASI) · doi:10.1109/iwasi58316.2023.10164335 · Cited by 9
Shinkuma, R., Nishio, T., Inagaki, Y., et al. (2020) · EURASIP Journal on Wireless Communications and Networking · doi:10.1186/s13638-020-01709-1 · Cited by 9
Zhou, C., Wu, W. R., He, H., Yang, P., Lyu, F., Cheng, N., Xuemin, & Shen (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.01471 · Cited by 9
“Within this paradigm, IoT devices can offload computing tasks to nearby terrestrial base stations (BSs), which can not only reduce the latency of task execution, but also save the power consumption of IoT devices [7].”
BackgroundFrom Semantic Communication to Semantic-aware Networking: Model, Architecture, and Open ProblemsPreprint
Shi, G., Xiao, Y., Li, Y., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.15405 · Cited by 9
“We propose a novel architecture based on federated edge intelligence [10]–[12] that has the potential to address the above challenges mentioned in Section III.”
MethodSalhaoui, M. (2021) · Digital Repository (Polytechnic University of Cartagena) · doi:10.31428/10317/10416 · Cited by 7
Comprehensive Analysis of Privacy Preserving Data Mining Algorithms for Future Develop Trends
Gautam, S., & Mittal, P. (2022) · International Research Journal of Computer Science · doi:10.26562/irjcs.2022.v0910.01 · Cited by 8
Effective networking: Enabling effective communications towards 6G
Soyak, E. G., & Erçetin, Ö. (2023) · Computer Communications · doi:10.1016/j.comcom.2023.12.002 · Cited by 8
Zou, X., Chen, C., Lin, P.-Y., Zhang, L., Xu, Y., & Zhang, W. (2024) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2024.3369628 · Cited by 10
Li, L., Xu, G., Liu, Z., et al. (2024) · Computer Networks · doi:10.1016/j.comnet.2024.110633 · Cited by 8
TinyFL_HKD: Enhancing Edge AI Federated Learning With Hierarchical Knowledge Distillation Framework
Hung, C., Tsai, C.-Y., Wang, C.-C., & Lee, C. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3544861 · Cited by 8
“Zhou et al. [1] proposed different levels of edge computing concepts; in this article, the device side primarily focuses on inference, while training is constrained by hardware limitations.”
Song, Y., Pan, Z., Luo, C., Wang, Y., Zheng, T., Pan, Y., Bu, N., Xu, R., & Huo, N. (2025) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.5c01586 · Cited by 8
Wu, Z., Zhang, H., Li, L., et al. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3566384 · Cited by 8
“AI applications driven by EI technology provided significant benefits, including reduced latency, enhanced privacy protection, improved energy efficiency (EE), and alleviation of bandwidth constraints [2], [4].”
Real time wire rope detection method based on Rockchip RK3588
Qian, M., Wang, Y., Liu, S., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-16043-z · Cited by 8
A Survey of AI Inference Technologies for On-Device Systems
Wang, W., Li, K., Ji, B., Liu, X., Yu, J., & Wu, Q. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3613691 · Cited by 9
DVFS-Aware DNN Inference on GPUs: Latency Modeling and Performance Analysis
Han, Y., Nan, Z., Zhou, S., et al. (2025) · International Conference on Communications · doi:10.1109/icc52391.2025.11161883 · Cited by 8
“In MEC and edge intelligence [3] systems, dynamic voltage and frequency scaling (DVFS) [4] technique is commonly used to balance the performance of processors This work is supported in part by the National Natural Science Foundation of China under Grants 62341108, in part by the China Postdoctoral…”
A Survey on Computation Offloading and Current Trends
Kumar, A., & Pal, A. (2025) · IEEE Access · doi:10.1109/access.2025.3625187 · Cited by 8
“The feasibility and efficiency of computation offloading heavily depend upon the hardware capabilities across devices, edge servers, and cloud infrastructure [136], [137].”
Liu, W., Chang, C.-H., & Zhang, F. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.3046858 · Cited by 8
“EDGE artificial intelligence (AI) is an enabler of a variety of dazzling deep learning applications like personal assistant, smart home appliance and video surveillance [1].”
BackgroundCamera-Based Edge Analytics for Drilling Optimization
Gooneratne, C. P., Magana-Mora, A., Affleck, M., Otalvora, W. B. C., Zhan, G. D., & Moellendick, T. E. (2020) · IEEE International Conference on Edge Computing and Communications (EDGE) · doi:10.1109/edge50951.2020.00024 · Cited by 10
“Currently, deep-learning models for video processing have achieved outstanding results in different industries and applications, which enables the use of cameras as intelligent and autonomous sensing devices [13-19].”
BackgroundSparse and dense matrix multiplication hardware for heterogeneous multi-precision neural networks
Nunez-Yanez, J. L., & Hosseinabady, M. (2021) · Array · doi:10.1016/j.array.2021.100101 · Cited by 9
Hardware-Efficient Stochastic Binary CNN Architectures for Near-Sensor Computing
Parmar, V., Penkovsky, B., Querlioz, D., & Suri, M. (2022) · Frontiers in Neuroscience · doi:10.3389/fnins.2021.781786 · Cited by 8
“A fully binarized pipeline can allow executing computation at the edge, without relying on network communication with high-performance compute servers in order to perform floating-point computations (Zhou et al., 2019).”
MethodEnergy-Efficient Transmissions in Federated Learning-Assisted Cognitive Radio Networks
Hlophe, M. C., Maharaj, B. T., & Sande, M. M. (2021) · IEEE International Conference on Communication Technology (ICCT) · doi:10.1109/icct52962.2021.9657938 · Cited by 8
“…the computational resources now located outside the cloud - at the edge of the network, the MEC has naturally become a novel paradigm that eludes the long propagation delays brought in by transmitting data from communication devices to the mobile cloud computing infrastructures for processing [3].”
BackgroundMulti-Agent Deep Reinforcement Learning in Flying Ad-Hoc Networks for Delay-Constrained Applications
Grasso, C., Raftopoulos, R., & Schembra, G. (2022) · Procedia Computer Science · doi:10.1016/j.procs.2022.07.011 · Cited by 8
DNN Real-Time Collaborative Inference Acceleration with Mobile Edge Computing
Yang, R., Li, Y., He, H. X., & Zhang, W. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892582 · Cited by 8
“To address these issues, edge computing [4, 5] and edge intelligence [6] have been proposed to provide computing and storage services close to the data source to meet requirements such as low latency, scalability, and privacy.”
BackgroundZhang, X. L., Wang, Y., Cai, Y., He, Y., Chen, X., & Jin, S. (2022) · International Conference on Network and Information Systems for Computers (ICNISC) · doi:10.1109/icnisc57059.2022.00093 · Cited by 9
Self-citationHandling Data Handoff of AI-Based Applications in Edge Computing Systems
Scotece, D., Fiandrino, C., & Foschini, L. (2023) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2023.3267942 · Cited by 8
Cost-Aware Neural Network Splitting and Dynamic Rescheduling for Edge Intelligence
Luger, D., Aral, A., & Brandić, I. (2023) · doi:10.1145/3578354.3592871 · Cited by 8
“This shift of AI into an ES is called edge intelligence (EI) [7, 15], which can reduce latency [13] and improve privacy [1] significantly.”
BackgroundInternet of things challenges and future scope for enhanced living environments
Liu, J., Hu, H., Xu, W., & Luo, D. (2023) · Advances in computers · doi:10.1016/bs.adcom.2023.10.007 · Cited by 9
RISC-V Custom Instructions of Elementary Functions for IoT Endpoint Devices
Chen, Y., Wang, X., Song, S., et al. (2023) · IEEE Transactions on Computers · doi:10.1109/tc.2023.3336174 · Cited by 8
“However, with the rapid increase in the number of edge devices, existing cloud computing is becoming inefficient or unable to handle these massively distributed computing tasks, due to the network capacity, computing power, and delay requirement [4].”
BackgroundLi, Z., Zou, S., & Guo, S. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3349393 · Cited by 9
“W ITH the popularization of 5G, the volume of data generated by IoT devices is growing rapidly and will reach 175 ZB in 2025, promoting the wide spread of intelligent applications [1], [2].”
BackgroundTalaria: Interactively Optimizing Machine Learning Models for Efficient Inference
Hohman, F., Wang, C., Lee, J., Görtler, J., Moritz, D., Bigham, J. P., Ren, Z., Foret, C., Shan, Q., & Zhang, X. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642628 · Cited by 8
“However, for all the emphasis on evaluating model behavior, there are much fewer visualization tools that evaluate a model’s efficiency (e.g., latency and power consumption).”
The Entanglement of Communication and Computing in Enabling Edge Intelligence
Li, J., & Mahmoodi, T. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3391923 · Cited by 8
“Although the studies by Zhou et al. [9] and Wang et al. [10] comprehensively examine the EI applications and explore efficiency issues in EI implementation, they both have been published more than three years and fail to cover the latest advancements in EI.”
BackgroundA Secure Interconnected Autonomous System Architecture for Multi-Domain IoT Ecosystems
Xu, R., Nagothu, D., Chen, Y., Aved, A. J., Ardiles-Cruz, E., & Blasch, E. (2024) · IEEE Communications Magazine · doi:10.1109/mcom.001.2300354 · Cited by 10
“…methods, e.g., Generated Pre-trained Transformers (GPT), and SDN controllers, the domain service management layer provides edge intelligence [12] that achieves efficient resource coordination and secure user service provision. that it is for blockchain scenarios. multiple attractive…”
MethodEvolutionary Neural Architecture Search for Transferable Networks
Zhou, X., Liu, S., Qin, A. K., & Tan, K. C. (2024) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2024.3427763 · Cited by 9
Zhu, A. (2020) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2020.103782 · Cited by 8
RetractedEdge Computing in Healthcare Systems
Mulimani, M. S., & Rachh, R. R. (2021) · EAI/Springer Innovations in Communication and Computing · doi:10.1007/978-3-030-60265-9_5 · Cited by 8
Optimizing AI Service Placement and Computation Offloading in Mobile Edge Intelligence Systems
Lin, Z., Bi, S., & Zhang, Y. A. (2020) · Globecom · doi:10.1109/globecom42002.2020.9348232 · Cited by 8
“Specifically, edge servers can use the AI models to process the related computation offloading from mobile users to reduce their computation delay and energy consumption [2]–[4].”
MethodAnoGAN-Based Anomaly Filtering for Intelligent Edge Device in Smart Factory
Kim, D., Cha, J., Oh, S., & Jeong, J. (2021) · International Conference on Ubiquitous Information Management and Communication (IMCOM) · doi:10.1109/imcom51814.2021.9377409 · Cited by 13
“[10], Level 3 and Level 6 are compared and analyzed.”
BackgroundMethodInfluentialAgriEdge: Edge Intelligent 5G Narrow Band Internet of Drone Things for Agriculture 4.0
Bhattacharya, A., & De, D. (2021) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-030-71172-6_3 · Cited by 8
Performance Comparison of PoseNet Models on an AIoT Edge Device
Kim, M.-J., Hong, S.-P., Kang, M., et al. (2021) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2021.019329 · Cited by 8
Accuracy-Based Task Offloading and Resource Allocation for Edge Intelligence in IoT
Fan, W., Chen, Z., Su, Y., et al. (2021) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2021.3128911 · Cited by 8
Edge Caching in IoT Smart Environments: Benefits, Challenges, and Research Perspectives Toward 6G
Amadeo, M., Campolo, C., Ruggeri, G., & Molinaro, A. (2022) · Internet of things · doi:10.1007/978-3-031-15160-6_3 · Cited by 8
Metadata
- Authors
- Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J.
- Affiliations
- Sun Yat-sen University (CN)
- Arizona State University (US)
- Venue
- Proceedings of the IEEE
- Published
- 2019-08
- Volume
- 107
- Issue
- 8
- Pages
- 1738-1762
- ISSN
- 0018-9219 (ISSN-L)
- 1558-2256
- OpenAlex
- W2950865323
- Semantic Scholar
- 928cd808aba140ec298508df87c5579811ff2f41
- Cited by
- 2,455
- References
- 168
- Citations by year
- 2026: 455 · 2025: 352 · 2024: 332 · 2023: 363 · 2022: 370 · 2021: 341 · 2020: 215 · 2019: 26
- FWCI
- 130.23
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Proceedings of the IEEE (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Basic Research Program of China (2017YFB1001703)
- National Natural Science Foundation of China (U1711265, 61802449)
- Program for Guangdong Introducing Innovative and Entrepreneurial Teams (2017ZT07X355)
- Guangdong Natural Science Funds (2018A030313032)
- Fundamental Research Funds for the Central Universities (17lgjc40)
- Army Research Office (W911NF-16-1-0448)
- Defense Threat Reduction Agency (HDTRA1-13-1-0029)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Information Systems › Internet of Things and AI
- Keywords
- edge AI, edge computing, edge computing architecture, deep learning training, deep learning inference, Internet of Things, mobile computing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
