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 1,501–1,600 of 2,413
Li, D., Ke, Z., & Zhou, X. (2021) · ACM Symposium on QoS and Security for Wireless and Mobile Networks (Q2SWinet) · doi:10.1145/3479242.3487322 · Cited by 2
“Recently, with the cloud computing paradigm shift to the mobile edge computing, offloading object detection tasks to the edge servers becomes an promising approach [3, 26].”
BackgroundHealthcare data analytics for wearable sensors
Mahmud, M. S. (2022) · Elsevier eBooks · doi:10.1016/b978-0-12-821661-3.00007-0 · Cited by 2
Adversarially robust water quality assessment associated with power plants
Hao, J., & Tao, Y. (2022) · Energy Reports · doi:10.1016/j.egyr.2022.03.049 · Cited by 2
Edge computing: A soul to Internet of things (IoT) data
Singh, V., Bharti, A. K., & Chandra, N. (2022) · Elsevier eBooks · doi:10.1016/b978-0-12-824054-0.00021-6 · Cited by 2
Progressive-encoding-based transmission for DNN-enabled edge intelligence in unreliable network
Dong, L., Luo, H., Zhang, S., Ren, Y., Duan, M., & Qin, Y. (2022) · Theoretical Computer Science · doi:10.1016/j.tcs.2022.06.014 · Cited by 2
Meira, N. F. D. C., Silva, M. C., Vieira, C. B., Souza, A. C. C., & Oliveira, R. (2022) · Lecture notes in business information processing · doi:10.1007/978-3-031-08965-7_8 · Cited by 2
Ma, Y., Song, Q., Hu, M., & Zhu, X. (2022) · Neural Processing Letters · doi:10.1007/s11063-022-10951-1 · Cited by 2
“At present, there is a gradual development to push the frontier of artificial intelligence to the edge of the network, which will fully unleash the potential of edge big data [30], but in these existing applications, the size and efficiency of models are very limited.”
BackgroundLightweight Few-Shot Learning Based on Triple Information for Internet-of-Things Applications
Wang, Q., Li, X., Chen, W., Kong, D., & Ma, W. (2022) · IEEE Access · doi:10.1109/access.2022.3197912 · Cited by 2
Modulating Users’ Involvement in Interactive Machine Learning Solutions: A Model Cascade Strategy
Gómez–Carmona, O., Casado–Mansilla, D., López–de–Ipiña, D., & García-Zubía, J. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-031-21333-5_35 · Cited by 2
Synchronous Federated Learning Latency Optimization Based on Model Splitting
Chen, F., Shi, L., Shi, Y., Xu, J., & Ding, X. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19211-1_41 · Cited by 2
Towards Accurate Latency Prediction of DNN Layers Inference on Diverse Computing Platforms
Liu, G., Dai, F., Huang, B., et al. (2022) · IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · doi:10.1109/dasc/picom/cbdcom/cy55231.2022.9927862 · Cited by 2
“This linear regressionbased prediction model is a status quo approach in [19], which performs better than logistic-based prediction models.”
MethodA Fuzzy Logic based Offloading System for Distributed Deep Learning in Wireless Sensor Networks
Zenasni, N., Habib, C., & Nassar, J. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892817 · Cited by 2
“The consequence of this unification is to distribute the computation of the DL applications and thus to alleviate the problems mentioned above [12].”
BackgroundEfficiency of Smart AI-Based Voice Apps and Virtual Services Operating With Chatbots
Said, N. A., Gura, D. A., & Karlov, D. (2022) · MENDEL · doi:10.13164/mendel.2022.2.009 · Cited by 2
Space-Air-Ground-Aqua Integrated Intelligent Network: Vision, and Potential Techniques
Huang, J., Yin, J., & Wang, S. (2022) · International Conference on Mobility, Sensing and Networking (MSN) · doi:10.1109/msn57253.2022.00164 · Cited by 2
“Edge computing is gradually being combined with AI, giving rise to a new research area, namely, ‘edge intelligence’ or ‘edge AI’ [1-2].”
BackgroundTime-optimized sequential decision making for service management in smart city environments
ALFahad, S., Anagnostopoulos, C. B., & Kolomvatsos, K. (2023) · Journal of Smart Cities and Society · doi:10.3233/scs-220015 · Cited by 2
“These types of services are given in response to the need for processing data being gathered by IoT devices and, then, being sent to EC nodes [63].”
Edge ai technology in the defense industry via reinforcement learning in simulation environments
Mendı, A. F. (2023) · Gümüşhane Üniversitesi Fen Bilimleri Enstitüsü Dergisi · doi:10.17714/gumusfenbil.1266035 · Cited by 2
Performance Validation of Spectrum Sensing Using Kernelized Support Vector Machine Transformation
Reddy, S. L., & Meena, M. (2023) · Wireless Personal Communications · doi:10.1007/s11277-023-10662-3 · Cited by 2
“Imperative, Machine learning (ML) models can be utilized for pattern recognition, picture handling, edge registering, energy harvesting, and resource management [5]-[9], yet additionally be applied to classify correspondence signals [10], [11].”
BackgroundKilcioglu, E., Stupia, I., & Vandendorpe, L. (2023) · IEEE Access · doi:10.1109/access.2023.3314381 · Cited by 2
“Each layer contains multiple interconnected neurons that communicate with adjacent neurons in the subsequent layer via weight parameters [16].”
BackgroundSynFMPL: A Federated Meta Pseudo Labeling Framework with Synergetic Strategy
Peng, T.-H., Chiu, T.-C., Pang, A., et al. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10278862 · Cited by 2
“Along with the blooming of the big data era, edge intelligence [1] has become a popular topic in recent years.”
BackgroundSocial-Aware Distributed Meta-Learning: A Perspective of Constrained Graphical Bandits
Wang, S., Bian, S., Tang, Y., et al. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10278850 · Cited by 2
“With the proximity to data-generating edge devices, we can achieve low-latency training and exploit rich data in a distributed manner [4].”
BackgroundKilcioglu, E., Stupia, I., & Vandendorpe, L. (2023) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc56721.2023.10293767 · Cited by 2
“Hence, a single-layer computation can also be partitioned among multiple EDs to encourage parallel computation by making use of the communication opportunities around [1].”
BackgroundInfluentialJiang, H. (2023) · Internet Technology Letters · doi:10.1002/itl2.488 · Cited by 2
Stochastic memory device based on a bistable system model with a simple analog circuit
Muramatsu, S., Nishida, K., Ando, K., et al. (2024) · Nonlinear Theory and Its Applications IEICE · doi:10.1587/nolta.15.249 · Cited by 2
On-demand Privacy Preservation for Cost-Efficient Edge Intelligence Model Training
Zhou, Z., & Chen, X. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-31919-9_19 · Cited by 2
Self-citationTowards a Dynamic Edge AI Framework Applied to Autonomous Driving Cars
Muratore, G., Rincon, J. A., Julián, V., Carrascosa, C., Greco, G., & Fortino, G. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-51999-5_34 · Cited by 2
Dong, L., Zhai, Y., Wu, J., & Shen, J. (2021) · IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) · doi:10.1109/ccgrid51090.2021.00062 · Cited by 3
On the Performance of Deep Learning in the Full Edge and the Full Cloud Architectures
Benbarrad, T., Salhaoui, M., & Arioua, M. (2021) · International Conference on Networking, Information Systems & Security (NISS) · doi:10.1145/3454127.3457632 · Cited by 2
“et al [22] conducted a comprehensive survey of recent”
BackgroundMethodOptimal UAV Caching and Trajectory Design in the AGVN
Wu, H., Lyu, F., & Shen, X. (2021) · SpringerBriefs in computer science · doi:10.1007/978-3-030-88878-7_4 · Cited by 3
Qiu, T., Chen, N., & Zhang, S. (2022) · Springer eBooks · doi:10.1007/978-981-16-9609-1_9 · Cited by 2
Approximate Computing for Efficient Neural Network Computation: A Survey
Zhang, H., Asadikouhanjani, M., Han, J., Deivalakshmi, S., & Ko, S. (2012) · Springer eBooks · doi:10.1007/978-3-030-98347-5_16 · Cited by 2
Machine Intelligence at the Edge with Learning Centric Power AllocationPreprint
Wang, S., Wu, Y., Xia, M., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.04922 · Cited by 2
“Data sharing uses the edge to collect data generated from MTC devices for machine learning [4]–[7], while model sharing uses federated learning [8]–[11] to exchange model parameters (instead of data) between the edge and users.”
MethodChatterjee, B., Seo, D., Chakraborty, S., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.13003 · Cited by 2
“This has given rise to the paradigm of “edge intelligence” (EI) [14], [15], which incorporates processing and/or machine learning capabilities at the sensor node.”
Design Methods and Processes for ML/DL models
John, M. M. (2021) · doi:10.24834/isbn.9789178771998 · Cited by 4
Towards dependable 6G networksPreprint
Rodriguez, F., Ahmad, I., Huusko, J., & Seppänen, K. (2022) · doi:10.36227/techrxiv.20237358.v1 · Cited by 2
Borsci, S., Lehtola, V., Nex, F., Yang, M. Y., Augustijn, E.-W., Bagheriye, L., Brüne, C., Kounadi, O., Li, J. J., Moreira, J., et al. (2023) · doi:10.32920/23808690 · Cited by 2
Edge Computing in Educational Technology
Shidaganti, G. I., Raj, V. A., Raman, V. R. M., & Kumaran, S. (2025) · doi:10.1002/9781394314409.ch5 · Cited by 2
Nti, I. K., Manikanta, M. S., Alex, C., & Ning, L. J. (2025) · Research Square · doi:10.21203/rs.3.rs-8002082/v1 · Cited by 3
Learning and Energy Efficient Edge Intelligence: Data Partition and Rate Control
Li, X., Wang, S., Zhu, G., Zhou, Z., Huang, K., & Gong, Y. (2022) · International Conference on Communications · doi:10.1109/icc45855.2022.9838801 · Cited by 1
“Recent years have witnessed the revolutionary development of artificial intelligence (AI) [1] due to the strengthened computation capability of cloud servers and the tremendous data generated by Internet-of-Things (IoT) devices for model training [2].”
BackgroundSelf-citationUsing AI and IoT at the Edge of the network
Lakrouni, S., Sebgui, M., & Bah, S. (2022) · International Conference on Optimization and Applications (ICOA) · doi:10.1109/icoa55659.2022.9934603 · Cited by 2
“An edge device can be an IoT device or a phone device, an edge server can be a server attached to an access point ,a network gateway or a micro data center available for near nodes, they also vary in sizes [6].”
BackgroundDynamic Resource Allocation for Containerized Applications in Edge Computing
Li, N., Tan, Y., Wang, X., et al. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-0416-7_12 · Cited by 1
Architecture and Implementation of a patient criticality aware Edge-Cloud offloading technique
Menon, A. B., Rajeev, K., Jyothika, S., Ratheesh, K., & Pathinarupothi, R. K. (2023) · IEEE International Conference for Convergence in Technology (I2CT) · doi:10.1109/i2ct57861.2023.10126178 · Cited by 1
“Cloud services bridge the resource gap between mobile and resource-intensive applications, which can be used to advance software, platforms, and infrastructure in these areas [2].”
BackgroundChen, J., Huang, Y., Zhang, L., et al. (2024) · Mobile Networks and Applications · doi:10.1007/s11036-024-02317-9 · Cited by 1
“This advancement, however, comes at the expense of an increasing amount of network layers and a more complex model [10].”
Semantic-driven Performance Optimization for UAV Based Object Detection
Guo, J., & Zhu, K. (2023) · doi:10.1109/ithings-greencom-cpscom-smartdata-cybermatics60724.2023.00082 · Cited by 1
“Due to limited energy of the UAV, we offloaded video semantic extraction process to the mobile edge computing (MEC) server [9].”
MethodA Sequential Approach to Detect Drifts and Retrain Neural Networks on Resource-Limited Edge Devices
Sunaga, K., Yamada, T., & Matsutani, H. (2024) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2023edp7123 · Cited by 1
“In addition, edge intelligence [1] in which some machine learning tasks such as prediction are performed in the edge side is also becoming popular since performance and efficiency of edge devices have been improved significantly.”
BackgroundTinyML: principles and algorithms
Ghorpade, S. N., Chougule, S., Chaudhari, B. S., & Zennaro, M. (2024) · Elsevier eBooks · doi:10.1016/b978-0-44-322202-3.00009-9 · Cited by 2
Bai, J., Dai, Q., & Li, Y. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.050921 · Cited by 1
Kashyap, M., Chauhan, R., Patel, D., et al. (2024) · ITM Web of Conferences · doi:10.1051/itmconf/20246503015 · Cited by 1
Valaboju, S., Devi, T. R., Devi, D. G., & Sudheer, P. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-97-8031-0_25 · Cited by 1
Machine Learning Empowered IoT Devices, Analysis of Indoor and Outdoor Temperature and Health Risks
Sohail, A., & Ahmad, N. (2024) · Smart sensors, measurement and instrumentation · doi:10.1007/978-3-031-68602-3_3 · Cited by 1
Bouhamida, H. A., Merabet, B., Afif, B., Daikh, A. A., Medjadji, N., Boureguig, K., & Belaribi, F. Z. (2024) · STUDIES IN ENGINEERING AND EXACT SCIENCES · doi:10.54021/seesv5n2-553 · Cited by 1
A Survey on Securing Image-Centric Edge Intelligence
Li, T., Hu, H., Gabbouj, M., Ye, Q., Xiang, Y., Li, J., & Li, L. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3700792 · Cited by 1
Generative AI and Labour Market Research Interest Framework
Grigorescu, A., & Joita, F. (2024) · Holistica · doi:10.2478/hjbpa-2024-0011
Architectures for Self-Powered Edge Intelligence
Trivedi, A. R., Kung, J., & Ko, J. H. (2024) · Springer eBooks · doi:10.1007/978-981-97-9314-3_9 · Cited by 1
Slimming Edge AI: A Case Study of Gesture Recognition for Air Conditioner Control
Cho, L., Huang, C.-C., & Huang, C. (2024) · International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) · doi:10.1109/ispacs62486.2024.10868520 · Cited by 1
“To address these challenges, hardware-independent edge AI frameworks (classified as level 6 in [1]), such as the AI for embedded system (AIfES) [5], have been proposed.”
Scheduling Big Machine Learning Tasks on Clusters of Heterogeneous Edge Devices
Mathkar, S., Aiyer, S., Bapat, Y., et al. (2025) · doi:10.1109/comsnets63942.2025.10885761 · Cited by 1
“This spectrum of devices contributes to the distributed computing landscape at the edge of networks [1].”
Comparing Application-Level Hardening Techniques for Neural Networks on GPUs
Esposito, G., Guerrero-Balaguera, J.-D., Condia, J. E. R., & Reorda, M. S. (2025) · Electronics · doi:10.3390/electronics14051042 · Cited by 1
Delay-Optimized Task Scheduling Based on Deep Reinforcement Learning in Computing Power Networks
Tang, Q., Xu, D., Xie, R., Feng, L., Chen, T., & Huang, T. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-2468-3_39 · Cited by 1
Harnessing the Power of AI With Deep Learning: Innovations and Implications
Upender, T., Sathiyamoorthy, C., Udayakumar, K., Kirubakaran, D., Purushothaman, V., & Raja, K. T. (2025) · International Conference on Computational, Communication and Information Technology (ICCCIT) · doi:10.1109/icccit62592.2025.10928038 · Cited by 1
“IoT devices equipped with deep learning capabilities can perform real-time data analysis and decision-making at the edge, reducing latency and enhancing responsiveness [9][10].”
Opportunistic Information Bottleneck for Edge-Assisted Goal-Oriented Communications
Binucci, F., & Banelli, P. (2024) · 2018 52nd Asilomar Conference on Signals, Systems, and Computers · doi:10.1109/ieeeconf60004.2024.10942917 · Cited by 1
“…and Machine Learning (ML) [1] in many different scenarios, like Internet of Things (IoT) [2], Industry 4.0, smart cities [3], etc. Edge Intelligence (EI) [4] has recently emerged as a promising framework to enable cost effective AI/ML services through computational offloading to the network edge.”
InfluentialAtwal, S., Singh, D., & Chhabra, A. (2025) · doi:10.1109/ic363308.2025.10957326 · Cited by 1
“The paper " Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing "[7] by Zhou, Chen, Li, Zeng, Luo, and Zhang presents an insightful literature review that explores the integration of artificial intelligence (AI) with edge computing, shaping a paradigm known as…”
Rethinking timing residuals: advancing PET detectors with explicit TOF corrections
Naunheim, S., de Paiva, L. L., Nadig, V., et al. (2025) · Frontiers in Physics · doi:10.3389/fphy.2025.1570925 · Cited by 1
“This makes it especially suitable for the application in PET scanners minding edge-AI approaches [54, 55].”
Multi-objective Evolutionary Optimization of Virtualized Fast Feedforward Networks
Kilic, R. B., Yıldırım, K. S., & Iacca, G. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-90062-4_17 · Cited by 1
Inland waterway autonomous transportation: System architecture, infrastructure and key technologies
Chen, H., Wen, Y., Huang, Y., Song, L., & Sui, Z. (2025) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2025.100858 · Cited by 1
Mone, G. (2025) · Communications of the ACM · doi:10.1145/3722543 · Cited by 1
Co-Inference Over Wireless Multi - Hop Networks
Zhang, X., Lin, Z., Zhou, C., et al. (2025) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc61545.2025.10978661 · Cited by 1
Foundation of secured edge intelligence in CPS
Tian, P., Liao, W., Qian, C., Guo, Y., & Yu, W. (2025) · Elsevier eBooks · doi:10.1016/b978-0-44-326572-3.00021-8 · Cited by 1
Edge intelligence in smart agriculture CPS
Qian, M., Qian, C., & Yu, W. (2025) · Elsevier eBooks · doi:10.1016/b978-0-44-326572-3.00019-x · Cited by 1
Enhancing Low-Power VLSI Design through AI-Based Simulation and Optimization
Hundekari, S., Onumajuru, O. K., Multani, D., et al. (2025) · International Conference on Smart Technologies, Communication and Robotics (STCR) · doi:10.1109/stcr62650.2025.11018967 · Cited by 1
“In IES-PtG systems, since integration of power generation, transmission, distribution, and consumption is essential, RL is incorporated to adapt decisions as per changing workloads and energy demands [14].”
Cui, L., & Bulis, A. (2025) · Environment Technology Resources Proceedings of the International Scientific and Practical Conference · doi:10.17770/etr2025vol2.8585 · Cited by 4
“…of opportunities, such as enhancing customer interactions to boost consumer satisfaction [8], creating a seamless customer experience to increase appeal [9], and enabling retailers to adopt AI for improving corporate governance while significantly reducing major costs and time inefficiencies [10].”
Edge Intelligence in Autonomous Vehicle Navigation
Manivannan, S., Muralidharan, V., Senthil Kumar, G., Sundarambal, B., Kirubakaran, N., & Selvaganesan, C. (2025) · International Conference on Data Science and Business Systems (ICDSBS) · doi:10.1109/icdsbs63635.2025.11031927 · Cited by 2
“Research should address energy efficiency and resource allocation for smoother operations [4].”
Rasheed, I., & Mostafa, H. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111553 · Cited by 1
Foundation Forecasting in IoE Networks: When Generative AI Meets Programmable Edge Nodes
Marchetti, F., Picano, B., Seidenari, L., et al. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3595465 · Cited by 1
Blockchain-Enabled AI-Enhanced Sun Tracking System for Optimal Energy Management
Sharma, S., Sharma, V. K., & Mittal, P. (2025) · Advances in Science, Technology & Innovation/Advances in science, technology & innovation · doi:10.1007/978-3-031-80949-1_13 · Cited by 1
Over-the-Air Computation for Realizing Neural Link in In-Network AI Architectures
Cang, Y., Chen, M., & Huang, K. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3596344 · Cited by 1
“A S A key usage scenario of the sixth-generation (6G) mobile networks, edge artificial intelligence (AI) promises to automate operations of Internet-of-Things (IoT) applications by deploying AI and machine learning algorithms at the network edge where billions of mobile devices are located [1], [2].”
AN EFFICIENT YOLOV9 MODEL FOR CAR PARTS DETECTION AND SEGMENTATION
Vasanthi, P., & Basheera, S. (2025) · Telecommunications and Radio Engineering · doi:10.1615/telecomradeng.2025054287 · Cited by 1
WSCoach: Wearable Real-time Auditory Feedback for Reducing Unwanted Words in Daily Communication
Zhang, Y., Janaka, N. N. P. K., Ram, A., Yin, P., Tian, Y., Zhao, S., & Dragicevic, P. (2025) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3749531 · Cited by 1
“As edge computing capabilities continue to advance, future iterations may shift more of the processing directly onto the glasses themselves, further reducing the need for data transmission and minimizing the risk of data exposure [52, 89].”
On-the-Fly Generation-Quality Enhancement of Deep Code Models via Model Collaboration
Sun, W., G.Q.Huang, N. A., Yan, M. L., Liu, Z., Li, H., Lei, Y., & Lo, D. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3765752 · Cited by 2
“Despite the widespread adoption of deep learning models, real-world deployment scenarios increasingly involve edge computing due to bandwidth limitations, latency considerations, and network instability [92].”
Arnab, A. A., & Leung, H. (2025) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops67674.2025.11162413 · Cited by 1
“Bandwidth allocation ensures reliable data transmission [12].”
Edge AI and Federated LLMOps for Latency-Critical IoT Systems in Smart Infrastructure
Myakala, P. K., Kamatala, S., & Naayini, P. (2025) · International Conference on Intelligent Technologies (CONIT) · doi:10.1109/conit65521.2025.11167465 · Cited by 1
“During the process, the model snapshot is used locally for inference to make quick and context-specific predictions [15].”
Legal framework and regulatory policies for cyber edge computing systems
Musa, A., & Adebayo, A. O. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-34109-0.00014-0 · Cited by 1
A deep learning-based approach for a real-time diagnosis of skin diseases
Algaphari, G. H., Morshed, N. A. M., & Alaidarous, K. M. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11577-9 · Cited by 2
“Numerous research studies have discussed the convergence of edge, fog, and AI, along with their respective architectures [15–17].”
Cooperative Inference for Real-Time 3D Human Pose Estimation in Multi-Device Edge Networks
Choi, H.-H., Kim, K., Lee, K.-H., et al. (2025) · IEEE Transactions on Communications · doi:10.1109/tcomm.2025.3616229 · Cited by 1
“Architectures, frameworks, and key technologies have been introduced for collaborative DNN inference among end devices, edge servers, and cloud centers, considering the trade-off between computational costs and communication overheads [18], [19].”
Carbon-Neutralizing Edge AI Inference for Data Streams via Model Control and Allowance Trading
Zhang, Y., Jiao, L., Zhu, K., Xu, Y., & Zhang, L. (2025) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs63083.2025.00023 · Cited by 1
“Edge AI inference [1], [2] often entails the deployment of AI models across edge computing infrastructures, such as micro data centers or server clusters co-located with cellular base stations or WiFi access points.”
HyperGen: Optimizing Generative Inference with Long Prompts for Resource-Constrained Systems
Gong, L., Liu, K., Li, X., Han, S., Lee, P. P. C., Hu, Y., & Feng, D. (2025) · ACM SIGOPS Asia-Pacific Workshop on Systems (APSys) · doi:10.1145/3725783.3764409 · Cited by 1
E-M 2 : Efficient Multimodal Sensing via Adaptive Sensor-Computation Activation
Cui, J., & Zheng, T. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3623296 · Cited by 2
Enhancing federated discovery on the Web of things with distributed AI models
Llopis, J. A., Iribarne, L., Criado, J., et al. (2025) · World Wide Web · doi:10.1007/s11280-025-01383-7 · Cited by 1
“For other authors, it is a layer far from the devices, used as middleware between devices and external agents [25 ].”
Mobility-Aware Resource Provisioning for Edge-Assisted Extended Reality Services
Pei, Y., He, M., Hu, S., et al. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3633587 · Cited by 1
“To address this limitation, mobile edge computing o ff ers a promising solution by providing computing resources on edge servers for XR content rendering [6], [7].”
Unleashing innovation dynamism: Enabling influence of artificial intelligence on firms
Wei, F., Bi, P., & Weng, Y. (2025) · International Review of Financial Analysis · doi:10.1016/j.irfa.2025.104788 · Cited by 2
Dependency-aware task offloading and energy optimization in UAV-assisted MEC systems
Liang, Z., Ni, Y., Tao, H., et al. (2025) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-025-02162-x · Cited by 1
EdgeReasoning: Characterizing Reasoning LLM Deployment on Edge GPUs
Kubwimana, B., & Huang, Q. (2025) · IEEE International Symposium on Workload Characterization · doi:10.1109/iiswc66894.2025.00018 · Cited by 4
“The rapid advancement of autonomous systems—from robotics and drones to self-driving vehicles—has created an unprecedented demand for intelligent decision-making and reasoning capabilities at the edge [44].”
Psychologically responsive AI smart classroom: Technological and educational challenges
Rahman, R. J., Wunnava, A., Venugopal, V., Walia, A., Hasan, Y., Goyal, S., & Mounika, N. (2025) · Multidisciplinary Reviews · doi:10.31893/multirev.2025ss0104 · Cited by 1
Dynamic Error Correction for Memristive Devices via Passive Resistance-to-Time Encoding
Tompris, I., Chatzipaschalis, I. K., Fyrigos, I.-A., & Sirakoulis, G. C. (2025) · IEEE International Conference on Electronics, Circuits and Systems (ICECS) · doi:10.1109/icecs66544.2025.11270708 · Cited by 1
“Simultaneously, the Big Data problem presents challenges in data transfer and real-time processing, particularly for Edge Computing, where low-latency, efficient systems are crucial [2].”
Evaluating FPGA Architectures for Quantized CNN Inference in Construction Monitoring Applications
Nardes, G. B., Grignani, W., Rausch, T. H., et al. (2025) · IEEE International Conference on Electronics, Circuits and Systems (ICECS) · doi:10.1109/icecs66544.2025.11270495 · Cited by 1
“In particular, Convolutional Neural Networks (CNNs) excel at image classification but typically rely on cloud servers for inference, which incurs latency, high bandwidth demands, and poses privacy risks, making scalability difficult [4].”
Sarkar, A., Maity, P. P., Teshome, F. T., et al. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.111279 · Cited by 1
AGI-Enabled Solutions for Service Explosion in IoX: A Cyber-Physical-Social-Thinking Perspective
Wei, Q., Ning, H., Shi, F., et al. (2025) · ACM Computing Surveys · doi:10.1145/3785669 · Cited by 1
“Sets its own goals and creates entirely new learning paradigms and knowledge frameworks beyond human comprehension.”
Distributed Computing with Language Models at the Edge: A Framework and Prototype
Karthikeyan, D. K., Shanmugasundaram, R. K., Paavonen, A.-S., et al. (2025) · International Conference on the Internet of Things (IoT) · doi:10.1145/3770501.3770511 · Cited by 1
“These challenges arise both from the characteristics outlined earlier and those summarized in Table 1, which presents a range of CPS domains alongside their enabling technologies, key challenges, and deployment restrictions [2, 5, 18, 27, 29, 32].”
Othman, N. I., Syed, H. J., Ramly, A. M., et al. (2025) · Egyptian Informatics Journal · doi:10.1016/j.eij.2025.100859 · Cited by 1
Synergistic cloud-edge intelligence for real-time multimodal entity linking and knowledge retrieval
Chen, M., Zhang, T., Qi, P., et al. (2025) · Journal of Cloud Computing Advances Systems and Applications · doi:10.1186/s13677-025-00801-5 · Cited by 1
“On one hand, deploying models directly on edge devices offers low latency and preserves data privacy, which are critical for a fluid user experience [26, 30].”
Noise-Robust and Edge Deployable ML Framework for Predictive Maintenance of Industrial Motors
Zahra, F. T., Erciyes, A., & Soytürk, M. (2025) · doi:10.23919/pemwn67312.2025.11304069 · Cited by 1
Kashif, S., Omar, E., Hussain, M. Z., et al. (2025) · doi:10.1109/icosst69113.2025.11315205 · Cited by 1
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
