Federated Learning via Over-the-Air Computation
Open accessThe DOI matches its Crossref record; 61 of the 62 references it cites were found in a registry or an index.
Abstract
The stringent requirements for low-latency and privacy of the emerging high-stake applications with intelligent devices such as drones and smart vehicles make the cloud computing inapplicable in these scenarios. Instead, edge machine learning becomes increasingly attractive for performing training and inference directly at network edges without sending data to a centralized data center. This stimulates a nascent field termed as federated learning for training a machine learning model on computation, storage, energy and bandwidth limited mobile devices in a distributed manner. To preserve data privacy and address the issues of unbalanced and non-IID data points across different devices, the federated averaging algorithm has been proposed for global model aggregation by computing the weighted average of locally updated model at each selected device. However, the limited communication bandwidth becomes the main bottleneck for aggregating the locally computed updates. We thus propose a novel over-the-air computation based approach for fast global model aggregation via exploring the superposition property of a wireless multiple-access channel. This is achieved by joint device selection and beamforming design, which is modeled as a sparse and low-rank optimization problem to support efficient algorithms design. To achieve this goal, we provide a difference-of-convex-functions (DC) representation for the sparse and low-rank function to enhance sparsity and accurately detect the fixe…
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“For instance, over-the-air federated learning (FL) provides a collaborative ML framework to train a global statistical model over wireless networks without accessing edge devices' private raw data [31].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [31]
In the citing paper
“Specifically, the transmitted signals at edge devices are first multiplied by the fading channels and then superposed over-the-air with additive channel noise, resulting in a noisy weighted sum of transmitted signals [31].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [31]
In the citing paper
“Specifically, for edge training systems, we need to jointly optimize the subcarrier and bandwidth allocation [88], [90], [241], transmit power and receive beamforming [31], [48], [178], passive beamforming at RIS [48], [178], device selection [31], [242] and activity detection [76], local updates computation [92], and global aggregation frequency control [130], thereby reducing the optimality gap”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [31]
In the citing paper
“For instance, the group sparsity can represent the combinatorial variables for edge devices selection in FL [31], edge devices activity detection [76], and inference tasks selection [53].”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [31]
In the citing paper
“Most of the resource allocation problems in edge AI need to solve a series of nonconvex optimization problems, e.g., nonconvex sparse optimization for device selection in wireless FL, nonconvex quadratic programming for transceiver design in over-the-air FL [31], lowrank matrix optimization for interference management in edge device distributed inference [52], and unit modulus constrained phase”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [31]
2 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Hao, X.-B., & Zhang, G.-G. (2017) · Encycl. Semantic Comput. Robotic Intell. · doi:10.1142/s2425038416300184 · Cited by 86,401 · cited 1×
“THE astounding growth in data volume promotes widespread artificial intelligent applications such as image recognition and natural language processing [1], thanks to”
BackgroundLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Boyd, S., & Vandenberghe, L. (2004) · doi:10.1017/cbo9780511804441 · Cited by 56,601
Vorontsova, E., Hildebrand, R., Gasnikov, A. V., & Stonyakin, F. (2010) · Computer Vision · doi:10.1007/978-1-4614-5257-7_6 · Cited by 39,270 · cited 2×
“The resulting problem is known as the sum-of-infeasibilities in the literature of optimization [39].”
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215 · cited 7×
“In particular, the federated averaging (FedAvg) algorithm [12] turns out to be a promising way to efficiently average the locally updated model at each device with unbalanced and non-IID data, thereby reducing the number of communication rounds between the center node and the end devices.”
InfluentialFederated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3298981 · Cited by 6,322
Han, S., Mao, H., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1510.00149 · Cited by 4,662 · cited 1×
“To address this issue, there is a growing body of recent works to reduce the storage overhead, time and power consumption in the inference process using the model compression methods via hardware and software co-design [7], [8].”
MethodTowards Federated Learning at Scale: System Design
Bonawitz, K., Eichner, H., Grieskamp, W., Huba, D., Ingerman, A., Ivanov, V., Kiddon, C., Konečný, J., Mazzocchi, S., McMahan, H. B., et al. (2019) · arXiv · doi:10.48550/arxiv.1902.01046 · Cited by 2,334 · cited 2×
“It has promising applications [14], [15] such as smart retail, smart healthcare, financial services, mobile content predictions, etc.”
BackgroundFederated Learning with Non-IID Data
Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., & Chandra, V. (2018) · arXiv · doi:10.48550/arxiv.1806.00582 · Cited by 2,077 · cited 1×
“, the data is generated by distinct distributions across different devices), imposes significant statistical challenges to fit a mode from the non-IID data [13], [17].”
Background
Research works printed but not linked: 2
- rockafellar, 2015, Convex Analysis
- tao, 1997, Convex analysis approach to DC programming: Theory, algorithms and applications, Acta Math Vietn, 22, 289
Cited by
Items 101–200 of 999
Over-the-Air Computation for 6G: Foundations, Technologies, and Applications
Wang, Z., Zhao, Y., Zhou, Y., Shi, Y., Jiang, C., & Letaief, K. B. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3405448 · Cited by 165
“The scheduling policy is also developed in [173], [174], [185], targeting to restrict the model aggregation error caused by participating devices with varying channel conditions.”
BackgroundSelf-citationFederated Learning in Multi-RIS-Aided Systems
Ni, W., Liu, Y., Yang, Z., Tian, H., & Shen, X. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3130444 · Cited by 134
“3Unlike the conventional communicate-then-compute schemes, AirComp is capable of harnessing the channel interference to integrate communication and computation into one concurrent transmission [27]–[29].”
BackgroundMethodInfluentialTrustworthy Federated Learning via Blockchain
Yang, Z., Shi, Y., Zhou, Y., Wang, Z., & Yang, K. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3201117 · Cited by 122
“As a promising framework of trustworthy AI, federated learning (FL) has recently been proposed to guarantee data privacy in the AI model training process, which collaboratively trains a global AI model by coordinating multiple devices [5], [6].”
BackgroundSelf-citationContext-Aware Online Client Selection for Hierarchical Federated Learning
Qu, Z., Duan, R., Chen, L., Xu, J., Lu, Z., & Liu, Y. (2022) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2022.3186960 · Cited by 123
“However, it is not straightforward to apply existing client selection solutions [7], [15], [16] to HFL due to several unique challenges that HFL faces.”
BackgroundNi, W., Liu, Y., Eldar, Y. C., Yang, Z., & Tian, H. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3188544 · Cited by 123
“Compared with most existing FL proposals based on conventional orthogonal multiple access (OMA) [12]–[17], over-the-air FL (AirFL) allows all users to aggregate a shared model by utilizing the superposition property of the uplink wireless channel [18]–[23].”
BackgroundMethodLiu, P., Zhu, G., Wang, S., Jiang, W., Luo, W., Poor, H. V., & Cui, S. R. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3226836 · Cited by 123
“For example, the work in [9] optimized the receive beamforming at the edge server to maximize the number of participated edge devices at each iteration of FEEL under peak power constraints.”
BackgroundMethodCommunication-Efficient Stochastic Zeroth-Order Optimization for Federated Learning
Fang, W., Yu, Z., Jiang, Y., Shi, Y., Jones, C. N., & Zhou, Y. (2022) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2022.3214122 · Cited by 122
“AirComp has recently been adopted to support the implementation of FL over wireless networks [16], [35], [36], [37], [38], [39], where channel fading and receiver noise inevitably”
BackgroundMethodInfluentialSelf-citationAmiri, M. M., Duman, T. M., Gunduz, D., Kulkarni, S. R., & Poor, H. V. P. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3065920 · Cited by 98
“rage of the local model updates computed by the devices rather than each individual model update. Motivated by the additive nature of the wireless MAC, we consider an analog approach similarly to [9]–[11], [13], where the devices transmit their gradient estimates in an analog fashion without employing any channel codi…”
MethodInterference Management for Over-the-Air Federated Learning in Multi-Cell Wireless Networks
Wang, Z., Zhou, Y., Shi, Y., & Zhuang, W. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3180799 · Cited by 117
“The devices in each cell are uniformly and randomly distributed in a circle of radius ̺ ∈ [1, 20] meters centered at their home BS.”
BackgroundMethodInfluentialSelf-citationTransmission Power Control for Over-the-Air Federated Averaging at Network Edge
Cao, X., Zhu, G., Xu, J., & Cui, S. R. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3143217 · Cited by 136
“Then, by considering multi-antenna Air-FedAvg systems, a joint device scheduling and receive beamforming design was studied in [34], and a unit-modulus analog receive beamforming design was proposed in [35].”
MethodFederated Learning and Meta Learning: Approaches, Applications, and Directions
Liu, X., Deng, Y., Nallanathan, A., & Bennis, M. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3330910 · Cited by 138
“The OAC-based approach for fast global model aggregation in the uplink transmission was proposed in [173] to explore the superposition property of a wireless multi-access channel via the joint device selection and beamforming design.”
MethodFederated Learning Via Inexact ADMM
Zhou, S., & Li, G. Y. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3243080 · Cited by 126
“F EDERATED learning (FL), originated from [1], [2], gains its popularity recently due to its ability to address various applications, such as vehicular communications [3], [4], [5], [6], digital health [7], and mobile edge and over-the-air computing [8], [9], [10], [11].”
BackgroundA Quasi-Newton Method Based Vertical Federated Learning Framework for Logistic Regression
Yang, K., Fan, T., Chen, T., Shi, Y., & Yang, Q. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.00513 · Cited by 52
“A line of works [4, 5, 6] focus on the horizontal structure, in which each node has a subset of data instances with complete data attributes.”
BackgroundSelf-citationDecentralized Wireless Federated Learning With Differential Privacy
Chen, S., Yu, D., Zou, Y., Yu, J., & Cheng, X. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3145010 · Cited by 100
“In [6], [12], the wireless aggregation is accomplished by incorporating user scheduling through power control or beamforming to enhance the communication efficiency.”
InfluentialCost-Effective Federated Learning in Mobile Edge Networks
Luo, B., Li, X., Wang, S., Huang, J., & Tassiulas, L. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3118436 · Cited by 130
Wireless Networked Multirobot Systems in Smart Factories
Chen, K., Lin, S., Hsiao, J.-H., Liu, C., Molisch, A. F., & Fettweis, G. P. (2020) · Proceedings of the IEEE · doi:10.1109/jproc.2020.3033753 · Cited by 131
“The previous works on distributed/federated learning across different data sets in wireless networks are still minimal, including federated learning through digital and analog signal combining techniques [142]–[144] and performing computation offloading [145], [146].”
BackgroundToward Communication-Efficient Federated Learning in the Internet of Things With Edge Computing
Sun, H., Li, S., Yu, F. R., Qi, Q., Wang, J., & Liao, J. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2994596 · Cited by 95
“Then in [29], DC representation was proposed to induce sparsity and low-rankness of the model for fast global model aggregation.”
Task-Oriented Over-the-Air Computation for Multi-Device Edge AI
Wen, D., Jiao, X., Liu, P., Zhu, G., Shi, Y., & Huang, K. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3294703 · Cited by 108
“…AirComp has been a promising technique widely exploited in federated edge learning for communication efficiency enhancement (see, e.g., [38], [39], [40], [41], [42]) and in many other crtical tasks such as distributed localization and wireless control systems (see, e.g., [43] and references…”
Self-citationIntegrated Sensing and Edge AI: Realizing Intelligent Perception in 6G
Liu, Z., Chen, X., Hai, W., Wang, Z., Chen, X., Niyato, D. T., & Huang, K. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3592989 · Cited by 127
“Observing that the convergence performance of FL improves with the number of participating sensors, the authors in [154] have formulated the AirComp sensor scheduling problem as joint sensor selection and receive beamforming to maximize the number of scheduled sensors under an MSE requirement and…”
Zhao, T., Li, F., & He, L. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3170900 · Cited by 113
“The authors in [15] designed the joint device selection and beamforming scheme to achieve fast global model aggregation.”
BackgroundJoint Dynamic Passive Beamforming and Resource Allocation for IRS-Aided Full-Duplex WPCN
Hua, M., & Wu, Q.-Q. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3133491 · Cited by 94
Federated Learning via Unmanned Aerial Vehicle
Fu, M., Shi, Y., & Zhou, Y. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3303492 · Cited by 105
“For instance, to reduce model misalignment error incurred by stragglers in AirComp-based FL, the authors in [6] and [10] scheduled the devices with reliable channels for concurrent model uploading.”
BackgroundResultInfluentialSelf-citationNi, W., Liu, Y., Yang, Z., Tian, H., & Shen, X. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3181214 · Cited by 98
“k=1 sk, (10) the computation distortion of ŝ with respect to s is defined as MSE(ŝ, s) , E(|ŝ− s|(2)) [6], i.”
BackgroundMethodInfluentialOver-the-Air Computation via Reconfigurable Intelligent Surface
Fang, W., Jiang, Y., Shi, Y., Zhou, Y., Chen, W., & Letaief, K. B. (2021) · IEEE Transactions on Communications · doi:10.1109/tcomm.2021.3114791 · Cited by 93
“The estimated function at the AP is given by [13] where m ∈ C M and η denote the receive beamforming vector and the denoising factor at the AP, respectively.”
BackgroundSelf-citationConvergence of Federated Learning Over a Noisy Downlink
Amiri, M. M., Gündüz, D., Kulkarni, S. R., & Poor, H. V. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3103874 · Cited by 108
“Furthermore, FEEL over wireless networks with a multi-antenna PS is studied in [18]–[22], where beamforming techniques are used for efficient gradient aggregation at the PS.”
MethodHua, M., Wu, Q., Yang, L., Schober, R., & Poor, H. V. (2021) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2021.3135603 · Cited by 90
“It is worth pointing out that ∂ V r 2 can be calculated from Proposition 4 of reference [43] and is given by where v p denotes the eigenvector corresponding to the largest eigenvalue of V .”
BackgroundChen, R., Li, L., Xue, K., Zhang, C., Pan, M., & Fang, Y. M. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3213766 · Cited by 108
“Moreover, among the previous works, the targeted learning models are either relatively simple (i.e., with convex loss functions) or shallow networks [14], [15], [16], [17], which is inconsistent with the current trend of the overparameterized DL models.”
BackgroundResultMatching-Theory-Based Low-Latency Scheme for Multitask Federated Learning in MEC Networks
Chen, D., Hong, C. S., Wang, L., Zha, Y., Zhang, Y., Liu, X., & Han, Z. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3053283 · Cited by 104
“[12] proposes an over-the-air computation based approach for the fast global aggregation process so as to maximize the number of participants under limited bandwidth, which can improve the accuracy of federated learning.”
BackgroundMethodApplications of Distributed Machine Learning for the Internet-of-Things: A Comprehensive Survey
Le, M., Huynh‐The, T., Do‐Duy, T., Vu, T.-H., Hwang, W., & Pham, Q. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3427324 · Cited by 120
“For example, the principle of over-the-air computation (labeled as OAC or AirComp in the literature) can be applied to speed up the model aggregation in FL with digital beamforming [31] and analog beamforming [32], and in SL over multi-antenna networks [33].”
An Overview on Over-the-Air Federated Edge Learning
Cao, X., Lyu, Z., Zhu, G., Xu, J., Xu, L.-X., & Cui, S. (2022) · IEEE wireless communications · doi:10.1109/mwc.005.2300016 · Cited by 83
“Next, the joint design of device scheduling and receive beamforming was presented in [8], in which the devices with weak signal strengths after receive beamforming were dropped from the training process.”
MethodFederated Continuous Learning With Broad Network Architecture
Le, J., Lei, X., Mu, N., Zhang, H., Zeng, K., & Liao, X. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3090260 · Cited by 101
“For the privacy issues, the methods based on differential privacy [35], [36]; secure multiparty computation [37], [38]; homomorphic encryption [39]; and over-the-air computation [40] are used to additionally improve privacy protection.”
MethodJoint Device Selection and Power Control for Wireless Federated Learning
Guo, W., Li, R., Huang, C., Qin, X., Shen, K., & Zhang, W. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.48550/arxiv.2205.09306 · Cited by 80
“Compared to the previous works that only account for the uplink communications of FL [17], [19]–[24] and only focus on the convergence analysis for FL [26]–[28], the goals of this paper are not only to investigate the impact of both the downlink and uplink wireless communications on the convergence behavior of the con…”
InfluentialFederated vs. Centralized Machine Learning under Privacy-elastic Users: A Comparative Analysis
Drainakis, G., Katsaros, K. V., Pantazopoulos, P., Sourlas, V., & Amditis, A. (2020) · IEEE International Symposium on Network Computing and Applications (NCA) · doi:10.1109/nca51143.2020.9306745 · Cited by 119
“On the other hand, while there is considerable effort in optimizing FL techniques e.g. , in terms of communication efficiency [8] or bandwidth efficiency [9], the focus is on privacy-sensitive only environments, and hence an extensive evaluation and comparison with the CL alternative is missing.”
BackgroundData-Importance Aware User Scheduling for Communication-Efficient Edge Machine Learning
Liu, D., Zhu, G., Zhang, J., & Huang, K. (2020) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2020.2999606 · Cited by 92
“topics such as RRM [9]–[15], multiple access [16]–[18], and signal encoding [19]–[21].”
BackgroundA Comprehensive Survey on Communication-Efficient Federated Learning in Mobile Edge Environments
Jia, N., Qu, Z., Ye, B., Wang, Y., Hu, S., & Guo, S. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3535957 · Cited by 107
“In order to enhance the sparsification, Yang et al. [182] formulate a joint optimization problem.”
Online Client Selection for Asynchronous Federated Learning With Fairness Consideration
Zhu, H., Zhou, Y., Qian, H. L., Shi, Y., Chen, X., & Yang, Y. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3211998 · Cited by 105
“Additionally, the authors in [12], [13], [14], [15], [16], and [17] jointly optimized wireless resource allocation (e.g., bandwidth allocation, beamforming design) and client selection.”
BackgroundSelf-citationSalau, B. A., Rawal, A., & Rawat, D. B. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3170449 · Cited by 106
“For instance federated learning has been applied to handle scalability between the radio resources block and number of devices in a network, network overload and power allocation [47], [87], [46].”
Joint Optimization of Communications and Federated Learning Over the Air
Fan, X., Wang, Y., Huo, Y., & Tian, Z. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3130111 · Cited by 86
“There are some pioneering works on analog aggregation based FL [13]–[18], most of which focus on designing transmission schemes [13]–[16].”
BackgroundReputation-enabled Federated Learning Model Aggregation in Mobile Platforms
Wang, Y., & Kantarcı, B. (2021) · International Conference on Communications · doi:10.1109/icc42927.2021.9500928 · Cited by 54
“The authors in [17] improve aggregation by adopting a difference-of-convex (DC) functions algorithm.”
MethodCooperative Interference Management for Over-the-Air Computation Networks
Cao, X., Zhu, G., Xu, J., & Huang, K. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.3043787 · Cited by 82
“The simple transmission scheme of channel inversion is widely adopted in the AirComp literature to overcome fading so that multiuser signals arriving at an AP are aligned in magnitude, which is required for receiving a desired functional value of distributed data [5], [8], [13], [14].”
BackgroundMethodHybrid Beamforming for Massive MIMO Over-the-Air Computation
Zhai, X., Chen, X., Xu, J., & Kwan Ng, D. W. (2021) · IEEE Transactions on Communications · doi:10.1109/tcomm.2021.3051397 · Cited by 74
“l IoT applications, the AP may be interested in computing a certain function value (e.g., the sum value) of the aggregated data rather than the individual messages (e.g., in federated learning setups [3]). In this case, the above conventional multiple access scheme may not be energy- or spectral-efficient and may also…”
BackgroundReconfigurable Intelligent Surface for Green Edge Inference
Hua, S., Zhou, Y., Yang, K., Shi, Y., & Wang, K. (2021) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2021.3058657 · Cited by 74
“As pointed out in [45], [46], the performance of SDR degrades sharply as the problem size grows.”
BackgroundSelf-citationMassive Digital Over-the-Air Computation for Communication-Efficient Federated Edge Learning
Qiao, L., Gao, Z., Mashhadi, M. B., & Gündüz, D. (2024) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2024.3431572 · Cited by 81
“Note that all the participating devices are synchronized in time in [10], [11], [12], [13], [14], and [15].”
BackgroundMethodContext-Aware Multi-User Offloading in Mobile Edge Computing: a Federated Learning-Based Approach
Shahidinejad, A., Farahbakhsh, F., Ghobaei‐Arani, M., Malik, M. H., & Anwar, T. (2021) · Journal of Grid Computing · doi:10.1007/s10723-021-09559-x · Cited by 85
“They used the difference of convex functions (DC) representation for sparse and low-rank function [34].”
MethodA Compressive Sensing Approach for Federated Learning Over Massive MIMO Communication Systems
Jeon, Y., Amiri, M. M., Li, J., & Poor, H. V. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.3038407 · Cited by 91
“Specifically, joint optimization for device selection and receive beamforming is proposed in [26], while joint design of transmit and receive beamforming is proposed in [27].”
BackgroundMethodBao, W., Wu, C., Guleng, S., Zhang, J., Yau, K.-L. A., & Ji, Y. (2021) · China Communications · doi:10.23919/jcc.2021.06.004 · Cited by 71
“Yang et al. [17] propose a client selection approach that takes into account the wireless connection between the central server and clients.”
BackgroundWireless Federated Learning Over Resource-Constrained Networks: Digital Versus Analog Transmissions
Yao, J., Xu, W., Yang, Z., You, X., Bennis, M., & Poor, H. V. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3407822 · Cited by 73
“Considering multi-antenna scenarios, the beamforming design at the receiver was optimized by solving a sparse and low-rank optimization problem in [33].”
MethodFederated Learning Over Multihop Wireless Networks With In-Network Aggregation
Chen, X., Zhu, G., Deng, Y., & Fang, Y. M. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3168538 · Cited by 82
“In each round, being consistent with [16], [29], our design goal is to aggregate as many model updates as possible at GBS given a predefined deadline D and resource constraints .”
Background1-Bit Compressive Sensing for Efficient Federated Learning Over the Air
Fan, X., Wang, Y., Huo, Y., & Tian, Z. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3209190 · Cited by 80
“Different from [17], [18], [19], [21] developed on the assumption that the local updates have to follow independent and identically distributed (IID) with zero mean”
BackgroundMethodInfluentialIntelligent Reflecting Surface Enabled Multi-Target Sensing
Meng, K., Wu, Q., Schober, R., & Chen, W. (2022) · IEEE Transactions on Communications · doi:10.1109/tcomm.2022.3217564 · Cited by 64
“By adopting the difference-of-convex-functions method [46], the non-convex rank-one constraint in (13c) can be equivalently expressed as”
MethodFederated Learning Versus Classical Machine Learning: A Convergence ComparisonPreprint
Asad, M., Moustafa, A., & Itō, T. (2021) · arXiv.org · doi:10.22541/au.162074596.66890690/v1 · Cited by 98
“This communication overhead can be measured either by uploading the gradients or through the communication rounds between the central server and participants [10].”
MethodA Graph Neural Network Learning Approach to Optimize RIS-Assisted Federated Learning
Wang, Z., Zhou, Y., Zou, Y., An, Q., Shi, Y., & Bennis, M. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3239400 · Cited by 77
Self-citationIntelligent Radio Signal Processing: A Survey
Pham, Q., Nguyen, N. T., Huynh‐The, T., Le, L. B., Lee, K., & Hwang, W. (2021) · IEEE Access · doi:10.1109/access.2021.3087136 · Cited by 99
“for FL via over-the-air computation in [158] or to enhance the passive beamforming performance and user privacy in”
BackgroundMethodBlind Over-the-Air Computation and Data Fusion via Provable Wirtinger Flow
Dong, J., Shi, Y., & Ding, Z. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2020.2970338 · Cited by 65
“Recently, the papers [15], [16] exploited AirComp in a federated learning system to support fast global model aggregation for locally updated model on each device.”
BackgroundSelf-citationFederated Learning for Cyber Physical Systems: A Comprehensive Survey
Quan, M. K., Pathirana, P. N., Wijayasundara, M., Setunge, S., Nguyen, D. C., Brinton, C. G., Love, D. J., & Poor, H. V. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3570288 · Cited by 96
“The technique proposed in the publication [236] aims to improve the number of clients whose mean-squared-error criterion may be satisfied during each global iteration by combining beamforming with client selection.”
Optimal Online Data Partitioning for Geo-Distributed Machine Learning in Edge of Wireless Networks
Lyu, X., Ren, C., Ni, W., Tian, H., Liu, R. P., & Dutkiewicz, E. (2019) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2019.2934002 · Cited by 69
“As typically assumed in federated learning in edge networks [13], [15], a sufficiently large set of data randomly selected in an unbiased fashion from a data source provides good representativeness of the source (or in other words, the randomly selected, unbiased set of data follows the same distribution as the entire…”
BackgroundMethodWang, S., Hosseinalipour, S., Gorlatova, M. A., Brinton, C. G., & Chiang, M. (2022) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2022.3216326 · Cited by 78
Empirical Studies of Institutional Federated Learning For Natural Language Processing
Zhu, X., Wang, J., Hong, Z., & Xiao, J. Z. (2020) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2020.findings-emnlp.55 · Cited by 73
“In addition, more business-to-client model training applications are drawing intensive attention of the public (Lim et al., 2020; Yang et al., 2020; Kong et al., 2020).”
BackgroundDelay Minimization for Federated Learning Over Wireless Communication NetworksPreprint
Yang, Z., Chen, M., Saad, W., Hong, C. S., Shikh‐Bahaei, M., Poor, H. V., & Cui, S. R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.03462 · Cited by 77
“Some of the challenges of FL over wireless networks have been studied in (Zhu et al., 2018b; Ahn et al., 2019; Yang et al., 2018; Zeng et al., 2019; Chen et al., 2019; Tran et al., 2019).”
BackgroundMethodFederated Reinforcement Learning for Electric Vehicles Charging Control on Distribution Networks
Qian, J., Jiang, Y., Liu, X., Wang, Q., Wang, T., Shi, Y., & Chen, W. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3306826 · Cited by 74
“To tackle the above issues, we propose an approach that leverages optimal power flow (OPF) [41] to model radial distribution networks (RDNs) [42] and federated learning (FL) [43], [44], [45], [46], [47] for charging control policy training.”
MethodSelf-citationFaithful Edge Federated Learning: Scalability and Privacy
Zhang, M., Wei, E., & Berry, R. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3118423 · Cited by 72
Update Aware Device Scheduling for Federated Learning at the Wireless Edge
Amiri, M. M., Gunduz, D., Kulkarni, S. R., & Vincent Poor, H. (2020) · 2020 IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit44484.2020.9173960 · Cited by 67
“Beamforming techniques at a multi-antenna PS for increasing the number of participating devices and overcoming the lack of CSI at the devices are introduced in [12] and [13], respectively.”
MethodEdge Federated Learning via Unit-Modulus Over-The-Air Computation
Wang, S., Hong, Y., Wang, R., Hao, Q., Wu, Y., & Ng, D. W. K. (2022) · IEEE Transactions on Communications · doi:10.1109/tcomm.2022.3153488 · Cited by 71
Federated Learning: A Distributed Shared Machine Learning Method
Hu, K., Li, Y., Xia, M., Wu, J., Lu, M., Zhang, S., & Weng, L. (2021) · Complexity · doi:10.1155/2021/8261663 · Cited by 76
“[22] put forward a logical regression method of center-based vertical FL, which realizes logical regression in vertical learning, and the objective function is as follows:”
MethodPrivacy Amplification for Federated Learning via User Sampling and Wireless Aggregation
Seif, M., Chang, W.-T., & Tandon, R. (2021) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit45174.2021.9518031 · Cited by 14
“In [12], [13], wireless aggregation is done by aligning the gradients through power control or beamforming.”
MethodBandwidth Allocation for Multiple Federated Learning Services in Wireless Edge Networks
Xu, J., Wang, H., & Chen, L. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3113346 · Cited by 79
“, using a hierarchical FL network architecture [24] that allows partial model aggregation, and leveraging the wireless transmission property to perform analog model aggregation over the air [25], [26].”
MethodExploring the key technologies and applications of 6G wireless communication network
Li, P., Fan, J., & Wu, J. (2025) · iScience · doi:10.1016/j.isci.2025.112281 · Cited by 72
“Its unique quantum state properties provide unbreakable security for communication systems, 75 ensuring the integrity and security of information.”
Combating Interference for Over-the-Air Federated Learning: A Statistical Approach via RIS
Shi, W., Yao, J., Xu, W., Xu, J., You, X., Eldar, Y. C., & Zhao, C. (2025) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2025.3536023 · Cited by 69
“To support simultaneous massive uplink transmission and enhance the communication efficiency of wireless FL, over-the-air computation (AirComp) has emerged as a promising solution [10], [11], [12].”
Joint Parameter-and-Bandwidth Allocation for Improving the Efficiency of Partitioned Edge Learning
Wen, D., Bennis, M., & Huang, K. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2020.3021177 · Cited by 64
“ion, many techniques are designed for efficient transportation of high-dimensional data over wireless channels. New multi-access schemes for FEEL, called “over-the-air computing”, are proposed in [16]–[18] to support fast 4 “over-the-air” model/gradient aggregation using the waveform superposition property of a multiac…”
BackgroundIntegrated Sensing-Communication-Computation for Edge Artificial Intelligence
Wen, D., Li, X., Zhou, Y., Shi, Y., Wu, S., & Jiang, C. (2024) · IEEE Internet of Things Magazine · doi:10.1109/iotm.001.2300146 · Cited by 59
“The information of sensing target extracted from the statistic information of the MLE).”
MethodSelf-citationApplication of cell-free massive MIMO in 5G and beyond 5G wireless networks: a survey
Obakhena, H. I., Imoize, A. L., Anyasi, F. I., & Kavitha, K. V. N. (2021) · Journal of Engineering and Applied Science · doi:10.1186/s44147-021-00014-y · Cited by 87
“Currently, federated learning (FL) frameworks are introduced in [72, 73], and FL optimization techniques have been presented in [74 – 76].”
Revisiting Analog Over-the-Air Machine Learning: The Blessing and Curse of Interference
Yang, H. H., Chen, Z., Quek, T. Q. S., & Poor, H. V. (2021) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2021.3139231 · Cited by 62
“In the presence of channel fading, it is suggested to invert the channel via power control at the end-user devices where the nodes that encounter deep fades suspend their transmissions [10], [11].”
Blockchain-Federated-Learning and Deep Learning Models for COVID-19 Detection Using CT Imaging
Kumar, R., Khan, A. A., Kumar, J., Zakria, Golilarz, N. A., Zhang, S., Ting, Y., Zheng, C., & Wang, W. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3076767 · Cited by 57
“The hospitals can share the dataset during training and information about their dataset is revealed through analyzing the distributed model [70], [16], [71], [72], [73], [74], [75], [76], [77].”
MethodDifferentially Private Aircomp Federated Learning with Power Adaptation Harnessing Receiver Noise
Koda, Y., Yamamoto, K., Nishio, T., & Morikura, M. (2020) · Globecom · doi:10.1109/globecom42002.2020.9322199 · Cited by 68
“For example, this goal can be achieved by enhancing the received signal-to-noise ratio (SNR) using user scheduling [6] or by minimizing the mean squared error (MSE) between the desired computation results and received symbols through transmit power control [8], analog beamforming [7], multipleinput–multiple-output (MI…”
Collaborative Machine Learning at the Wireless Edge with Blind Transmitters
Amiri, M. M., Duman, T. M., & Gunduz, D. (2019) · 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) · doi:10.1109/globalsip45357.2019.8969185 · Cited by 58
“A single-input multiple-output (SIMO) wireless fading MAC is studied in [8], where a beamforming technique is designed to maximize the number of devices participating in each iteration, while keeping the quality of the received signal at the PS above the specified threshold level.”
MethodOver-the-Air Machine Learning at the Wireless Edge
Amiri, M. M., & Gündüz, D. (2019) · 2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc.2019.8815402 · Cited by 60
“A SIMO wireless MAC with beamforming is considered in [11] for distributed learning, where the goal is to maximize the number of workers scheduled for transmission with an acceptable quality for the retrieved signal.”
BackgroundOptimal Power Control for Over-the-Air Computation
Cao, X., Zhu, G., Xu, J., & Huang, K. (2019) · Globecom · doi:10.1109/globecom38437.2019.9013170 · Cited by 26
“Despite extensive research progress, most prior work on AirComp assumes the simple channel inversion power control at devices, such that their transmitted signals are perfectly aligned in magnitude at the FC receiver to yield the desired function [3], [4], [10].”
BackgroundIntegrated Sensing, Communication, and Computation for Over-the-Air Federated Edge Learning
Wen, D., Xie, S., Cao, X., Cui, Y., Xu, J., Shi, Y., & Cui, S. R. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3598997 · Cited by 56
“The delay of local model aggregation in Air-FEEL is shown to be irrelevant to the number of participating devices, thus leading to a significant enhancement of communication efficiency [6], [7], [8], [9].”
Self-citationFederated learning and TinyML on IoT edge devices: Challenges, advances, and future directions
Ramadan, M. N. A., Ali, M. A. H., Khoo, S. Y., & AlKhedher, M. A. (2025) · ICT Express · doi:10.1016/j.icte.2025.06.008 · Cited by 72
ChannelComp: A General Method for Computation by Communications
Razavikia, S., da Silva, J. M. B., & Fischione, C. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3324999 · Cited by 59
“Compared with standard schemes, analog technique AirComp can dramatically reduce the required communication resources, particularly in distributed learning, where it has also attracted growing attention for federated edge learning systems [19], [20].”
Over-the-air federated learning: Status quo, open challenges, and future directions
Xiao, B., Yu, X., Ni, W., Wang, X., & Poor, H. V. (2024) · Fundamental Research · doi:10.1016/j.fmre.2024.01.011 · Cited by 73
“after problem transformation [36] Effective user selection”
InfluentialMao, W., Lu, X., Jiang, Y., & Zheng, H. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3350050 · Cited by 72
“Though more clients can improve the convergence speed of FL, the limited bandwidth of WFLNs makes the communication delay longer when lots of clients uploading their local updates at once [11], [12], [13].”
BackgroundOver-the-Air Aggregation for Federated Learning: Waveform Superposition and Prototype Validation
Guo, H., Zhu, Y., Ma, H., Lau, V. K. N., Huang, K., Li, X., Nong, H., & Zhou, M. (2021) · Journal of Communications and Information Networks · doi:10.23919/jcin.2021.9663107 · Cited by 56
Federated Learning for Audio Semantic Communication
Tong, H., Yang, Z., Wang, S., Hu, Y., Semiari, O., Saad, W., & Yin, C. (2021) · Frontiers in Communications and Networks · doi:10.3389/frcmn.2021.734402 · Cited by 55
A Survey on Vertical Federated Learning: From a Layered PerspectivePreprint
Liu, Y., Chai, D., Zhang, J., Jin, Y., Wang, L., Liu, H., Han, T., Xu, Q., & Chen, K. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2304.01829 · Cited by 65
Over-the-Air Decentralized Federated Learning
Shi, Y., Zhou, Y., & Shi, Y. (2021) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit45174.2021.9517780 · Cited by 67
“The digital [14]–[16] and analog [17]–[19] transmission schemes have been proposed to support FL over wireless networks.”
BackgroundMethodSelf-citationData-Aware Device Scheduling for Federated Edge Learning
Taïk, A., Mlika, Z., & Cherkaoui, S. (2021) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2021.3100574 · Cited by 58
“This restriction often slows down the convergence of training [6, 5].”
Background6G-Enabled Smart Agriculture: A Review and Prospect
Zhang, F., Zhang, Y., Lu, W., Gao, Y., Gong, Y., & Cao, J. (2022) · Electronics · doi:10.3390/electronics11182845 · Cited by 73
“Other works in wireless AI are AI-based wireless network architecture [94], AI-based transport-layer congestion control [95], AI-based service rate con-trol [96], AI-based demand prediction and caching techniques [97], and AI-based wireless distributed computing [98].”
StarFL: Hybrid Federated Learning Architecture for Smart Urban Computing
Huang, A., Liu, Y., Chen, T., Zhou, Y., Sun, Q., Chai, H., & Yang, Q. (2021) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3467956 · Cited by 68
Relay-Assisted Cooperative Federated Learning
Lin, Z., Liu, H., & Zhang, Y. A. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3155596 · Cited by 61
“In [15], the authors considered joint device selection and beamforming design to maximize the number of selected devices under a target mean-square-error (MSE) requirement.”
BackgroundInfluentialUAV Aided Over-the-Air Computation
Fu, M., Zhou, Y., Shi, Y., Chen, W., & Zhang, R. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3134327 · Cited by 62
“The transmit signals after pre-processing at each sensor are give by where { s k [ n ] , ∀ k ∈ K} are assumed to be independent with each other and normalized with zero mean and unit variance, i.e., E ( s [12], [10].”
Self-citationResource Allocation for Latency-Aware Federated Learning in Industrial Internet of Things
Gao, W., Zhao, Z., Min, G., Ni, Q., & Jiang, Y. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3073642 · Cited by 68
“[25] leverage the signal superposition property of wireless multiple-access channel, and design a novel over-the-air computation approach to yield faster global model aggregation.”
MethodFederated Fine-Tuning for Pre-Trained Foundation Models Over Wireless Networks
Wang, Z., Zhou, Y., Shi, Y., & Letaief, K. B. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3531128 · Cited by 87
“To facilitate efficient high-dimensional model exchange under limited radio resources, various approaches have been explored in the context of conventional wireless FL, focusing on device scheduling [29], power allocation [30], [31], beamforming design [32], and bandwidth.”
Self-citationDecentralized Aggregation for Energy-Efficient Federated Learning via D2D Communications
Al-Abiad, M. S., Obeed, M., Hossain, M. J., & Chaaban, A. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3253718 · Cited by 67
“Another set of works investigated the impact of wireless link conditions, number of collaborating edge devices, and computation frequency allocation on the performance of star-based FL [10], [11], [12], [13].”
Background(2020) · doi:10.1007/978-981-15-6186-3 · Cited by 52
Satellite Federated Edge Learning: Architecture Design and Convergence Analysis
Shi, Y., Zeng, L., Zhu, J., Zhou, Y., Jiang, C., & Letaief, K. B. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3427377 · Cited by 68
“…for On-Board FEEL: Although the deployment of FEEL in terrestrial networks has been extensively studied and the solutions are relatively mature [26], [27], [28], implementing FEEL in LEO mega-constellation networks presents unique challenges due to the high mobility of satellites, i.e.,…”
BackgroundSelf-citationA Comprehensive Survey of 6G Wireless CommunicationsPreprint
Zhao, Y., Zhai, W., Zhao, J., Zhang, T., Sun, S., Niyato, D. T., & Lam, K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.03889 · Cited by 74
Federated Edge Learning for 6G: Foundations, Methodologies, and Applications
Tao, M., Zhou, Y., Shi, Y., Lu, J., Cui, S. R., Lü, J., & Letaief, K. B. (2024) · Proceedings of the IEEE · doi:10.1109/jproc.2024.3509739 · Cited by 58
“…By seamlessly integrating the computation and communication processes, AirComp is recognized as an effective scheme to support task-oriented model aggregation for FEEL, given its potential to mitigate the communication bottleneck problem during uplink model aggregation [13], [14], [18].”
Self-citationFederated Learning: Crop classification in a smart farm decentralised network
Idoje, G., Dagiuklas, T., & Iqbal, M. (2023) · Smart Agricultural Technology · doi:10.1016/j.atech.2023.100277 · Cited by 76
Ji, X., Tian, J., Zhang, H., Wu, D., & Li, T. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3233595 · Cited by 59
“Although empirical studies [16] and theoretical analysis [17] all show that more devices can accelerate the FL convergence, limited wireless network bandwidth cannot allow too many devices to upload their local model parameters simultaneously.”
Background
Metadata
- Authors
- Yang, K., Jiang, T., Shi, Y., & Ding, Z.
- Affiliations
- Chinese Academy of Sciences (CN)
- ShanghaiTech University (CN)
- University of California, Davis (US)
- Venue
- IEEE Transactions on Wireless Communications
- Published
- 2020-03
- Volume
- 19
- Issue
- 3
- Pages
- 2022-2035
- ISSN
- 1536-1276 (ISSN-L)
- 1558-2248
- OpenAlex
- W2999074226
- Cited by
- 1,084
- References
- 62
- Citations by year
- 2026: 86 · 2025: 154 · 2024: 176 · 2023: 190 · 2022: 189 · 2021: 190 · 2020: 80
- FWCI
- 63.79
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Wireless Communications (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (61601290)
- National Science Foundation (CNS-1702752, ECCS-1711823)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Communication Technologies
- Keywords
- federated learning, over-the-air computation, edge machine learning, model aggregation, device selection, beamforming design, difference of convex functions, DC algorithm, non-IID data, data privacy
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.
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.