Federated Learning: Challenges, Methods, and Future Directions
Open accessThe DOI matches its Crossref record; 92 of the 92 references it cites were found in a registry or an index.
Abstract
Federated learning involves training statistical models over remote devices or siloed data centers, such as mobile phones or hospitals, while keeping data localized. Training in heterogeneous and potentially massive networks introduces novel challenges that require a fundamental departure from standard approaches for large-scale machine learning, distributed optimization, and privacy-preserving data analysis. In this article, we discuss the unique characteristics and challenges of federated learning, provide a broad overview of current approaches, and outline several directions of future work that are relevant to a wide range of research communities.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
“Trusted Distributed AI extends the principles of federated and collaborative learning with trust guarantees, ensuring that distributed models can be trained and deployed without exposing sensitive data or compromising model integrity [235,236].”
From Anomaly detection and root-cause identification in microservices: a survey (2026) · cites this paper as [235]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The actual process for aggregating parameters depends on the network topology, as nodes might be segregated into sub-networks due to geographical or legal constraints (see Fig. 2).”
From The future of digital health with federated learning (2020) · cites this paper as [10]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“It is important to note that FL does not solve all potential privacy issues and—similar to ML algorithms in general—will always carry some risks.”
From The future of digital health with federated learning (2020) · cites this paper as [10]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“very little behavioral work has been done on eliciting preferences for differential privacy [144, 6].”
From Advances and Open Problems in Federated Learning (2021) · cites this paper as [6]
Experimental — accuracy not yet measuredIn the citing paper
“FL is a paradigm that aims to collaborate on data management and privacy issues by using evaluation metrics without transferring samples [47–49].”
From A comprehensive survey on federated learning techniques for healthcare informatics (2023) · cites this paper as [48]
2 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Boyd, S., Parikh, N., Chu, E., Peleato, B., & Eckstein, J. (2011) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000016 · Cited by 17,075
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 5×
“This has led to a growing interest in federated learning [31], which explores training statistical models directly on remote devices.”
BackgroundMethodInfluentialCalibrating Noise to Sensitivity in Private Data Analysis
Dwork, C., McSherry, F., Nissim, K., & Smith, A. (2006) · Lecture Notes in Computer Science · doi:10.1007/11681878_14 · Cited by 7,272
Federated 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 · cited 1×
“Federated learning methods have been deployed by major service providers [11, 124], and play a critical role in supporting privacy-sensitive applications where the training data are distributed at the edge [e.g., 5, 46, 51, 89, 105, 127, 139].”
MethodFog computing and its role in the internet of things
Bonomi, F., Milito, R., Zhu, J., & Addepalli, S. (2012) · Proceedings of the first edition of the MCC workshop on Mobile cloud computing · doi:10.1145/2342509.2342513 · Cited by 6,244
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2014) · Foundations and Trends® in Theoretical Computer Science · doi:10.1561/0400000042 · Cited by 5,557
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
Rastegari, M., Ordonez, V., Redmon, J., & Farhadi, A. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_32 · Cited by 4,408
Federated Optimization in Heterogeneous Networks
Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2018) · arXiv · doi:10.48550/arxiv.1812.06127 · Cited by 4,023 · cited 7×
“Indeed, when data is not identically distributed across devices in the network, methods such as FedAvg have been shown to diverge in practice [65, 75].”
BackgroundMethodInfluentialSelf-citationPractical Secure Aggregation for Privacy-Preserving Machine Learning
Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H. B., Patel, S., Ramage, D., Segal, A., & Seth, K. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3133982 · Cited by 3,956 · cited 1×
“quires that the updates are also private to the server. Current works that aim to improve the privacy of federated learning typically build upon previous classical cryptographic protocols such as SMC [10, 42] and differential privacy [3, 8, 41, 76]. Bonawitz et al. [10] introduce an SMC protocol to protect individual…”
BackgroundThe Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2013) · doi:10.1561/9781601988195 · Cited by 3,856
Research works printed but not linked: 56
- [77] L. Melis, G. Danezis, and E. D. Cristofaro. Efficient private statistics with succinct sketches. In Network and Distributed System Security Symposium , 2016. -
- [79] P. Mohassel and P. Rindal. Aby 3: a mixed protocol framework for machine learning. In Conference on Computer and Communications Security , 2018. -
- [80] M. Mohri, G. Sivek, and A. T. Suresh. Agnostic federated learning. In International Conference on Machine Learning , 2019. -
- [94] A. Reisizadeh, S. Prakash, R. Pedarsani, and A. S. Avestimehr. Coded computation over heterogeneous clusters. IEEE Transactions on Information Theory , 65:4227-4242, 2019. -
- [95] M. S. Riazi, C. Weinert, O. Tkachenko, E. M. Songhori, T. Schneider, and F. Koushanfar. Chameleon: A hybrid secure computation framework for machine learning applications. In Asia Conference on Computer and Communications Security , 2018. -
- [96] P. Richtárik and M. Takᡠc. Distributed coordinate descent method for learning with big data. Journal of Machine Learning Research , 17:2657-2681, 2016. -
- [97] B. D. Rouhani, M. S. Riazi, and F. Koushanfar. Deepsecure: Scalable provably-secure deep learning. In Design Automation Conference , 2018. -
- [98] S. Samarakoon, M. Bennis, W. Saad, and M. Debbah. Federated learning for ultra-reliable low-latency v2v communications. In Global Communications Conference , 2018. -
- [102] S. Shalev-Shwartz and T. Zhang. Accelerated mini-batch stochastic dual coordinate ascent. In Advances in Neural Information Processing Systems , 2013. -
- [103] O. Shamir and N. Srebro. Distributed stochastic optimization and learning. In Allerton Conference on Communication, Control, and Computing , 2014. -
- [105] S. Silva, B. Gutman, E. Romero, P. M. Thompson, A. Altmann, and M. Lorenzi. Federated learning in distributed medical databases: Meta-analysis of large-scale subcortical brain data. arXiv preprint arXiv:1810.08553 , 2018. - · arXiv
- [86] N. Papernot, S. Song, I. Mironov, A. Raghunathan, K. Talwar, and Ú. Erlingsson. Scalable private learning with pate. In International Conference on Learning Representations , 2018. -
- [87] A. Qiao, B. Aragam, B. Zhang, and E. Xing. Fault tolerance in iterative-convergent machine learning. In International Conference on Machine Learning , 2019. -
- [88] Z. Qu, P. Richtárik, and T. Zhang. Quartz: Randomized dual coordinate ascent with arbitrary sampling. In Advances in Neural Information Processing Systems , 2015. -
- [71] Y. Liu, J. K. Muppala, M. Veeraraghavan, D. Lin, and M. Hamdi. Data center networks: Topologies, architectures and fault-tolerance characteristics . Springer Science & Business Media, 2013. -
- [72] C. Ma, V. Smith, M. Jaggi, M. I. Jordan, P. Richtárik, and M. Takᡠc. Adding vs. averaging in distributed primal-dual optimization. In International Conference on Machine Learning , 2015. -
- [6] D. Anguita, A. Ghio, L. Oneto, X. Parra, and J. L. Reyes-Ortiz. A public domain dataset for human activity recognition using smartphones. In European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning , 2013. -
- [56] P. Jiang and G. Agrawal. A linear speedup analysis of distributed deep learning with sparse and quantized communication. In Advances in Neural Information Processing Systems , 2018. -
- [62] C.-P. Lee and D. Roth. Distributed box-constrained quadratic optimization for dual linear svm. In International Conference on Machine Learning , 2015. -
- [63] K. Lee, M. Lam, R. Pedarsani, D. Papailiopoulos, and K. Ramchandran. Speeding up distributed machine learning using codes. IEEE Transactions on Information Theory , 64:1514-1529, 2017. -
- [131] H. Yu, S. Yang, and S. Zhu. Parallel restarted sgd for non-convex optimization with faster convergence and less communication. In AAAI Conference on Artificial Intelligence , 2018. -
- [132] H. Yu, R. Jin, and S. Yang. On the linear speedup analysis of communication efficient momentum sgd for distributed non-convex optimization. In International Conference on Machine Learning , 2019. -
- [133] J. Yuan and S. Yu. Privacy preserving back-propagation neural network learning made practical with cloud computing. IEEE Transactions on Parallel and Distributed Systems , 25:212-221, 2013. -
- [134] M. Yurochkin, M. Agarwal, S. Ghosh, K. Greenewald, T. N. Hoang, and Y. Khazaeni. Bayesian nonparametric federated learning of neural networks. In International Conference on Machine Learning , 2019. -
- [135] H. Zhang, J. Li, K. Kara, D. Alistarh, J. Liu, and C. Zhang. ZipML: Training linear models with end-to-end low precision, and a little bit of deep learning. In International Conference on Machine Learning , 2017. -
- [1] Tensorflow federated: Machine learning on decentralized data. URL https://www.tensorflow.org/federated . -
- [2] M. Abadi, A. Chu, I. Goodfellow, H. B. McMahan, I. Mironov, K. Talwar, and L. Zhang. Deep learning with differential privacy. In Conference on Computer and Communications Security , 2016. -
- [137] Y. Zhang, J. Duchi, and M. Wainwright. Divide and conquer kernel ridge regression: A distributed algorithm with minimax optimal rates. Journal of Machine Learning Research , 16:3299-3340, 2015. -
- [140] F. Zhou and G. Cong. On the convergence properties of a k -step averaging stochastic gradient descent algorithm for nonconvex optimization. In International Joint Conference on Artificial Intelligence , 2018. -
- [141] M. Zinkevich, M. Weimer, L. Li, and A. J. Smola. Parallelized stochastic gradient descent. In Advances in Neural Information Processing Systems , 2010.
- [21] Z. B. Charles, D. S. Papailiopoulos, and J. Ellenberg. Approximate gradient coding via sparse random graphs. arXiv preprint arXiv:1711.0677 , 2017. -
- [22] K. Chaudhuri, C. Monteleoni, and A. D. Sarwate. Differentially private empirical risk minimization. Journal of Machine Learning Research , 12:1069-1109, 2011. -
- [23] D. Chaum. The dining cryptographers problem: Unconditional sender and recipient untraceability. Journal of Cryptology , 1:65-75, 1988. -
- [27] W. Dai, A. Kumar, J. Wei, Q. Ho, G. Gibson, and E. P. Xing. High-performance distributed ML at scale through parameter server consistency models. In AAAI Conference on Artificial Intelligence , 2015. -
- [28] O. Dekel, R. Gilad-Bachrach, O. Shamir, and L. Xiao. Optimal distributed online prediction using mini-batches. Journal of Machine Learning Research , 13:165-202, 2012. -
- [29] A. Deshpande, C. Guestrin, S. R. Madden, J. M. Hellerstein, and W. Hong. Model-based approximate querying in sensor networks. The VLDB Journal , 14:417-443, 2005. -
- [30] J. Duchi, M. I. Jordan, and B. McMahan. Estimation, optimization, and parallelism when data is sparse. In Advances in Neural Information Processing Systems , 2013. -
- [31] J. C. Duchi, M. I. Jordan, and M. J. Wainwright. Privacy aware learning. In Advances in Neural Information Processing Systems , 2012. -
- [32] C. Dwork. A firm foundation for private data analysis. Communications of the ACM , 54:86-95, 2011. -
- [37] T. Evgeniou and M. Pontil. Regularized multi-task learning. In Conference on Knowledge Discovery and Data Mining , 2004. -
- [39] M. Fredrikson, S. Jha, and T. Ristenpart. Model inversion attacks that exploit confidence information and basic countermeasures. In Conference on Computer and Communications Security , 2015. -
- [43] S. Goryczka and L. Xiong. A comprehensive comparison of multiparty secure additions with differential privacy. IEEE Transactions on Dependable and Secure Computing , 14:463-477, 2015. -
- [48] Q. Ho, J. Cipar, H. Cui, S. Lee, J. K. Kim, P. B. Gibbons, G. A. Gibson, G. Ganger, and E. P. Xing. More effective distributed ML via a stale synchronous parallel parameter server. In Advances in Neural Information Processing Systems , 2013. -
- [50] J. Huang, F. Qian, Y. Guo, Y. Zhou, Q. Xu, Z. M. Mao, S. Sen, and O. Spatscheck. An in-depth study of lte: effect of network protocol and application behavior on performance. SIGCOMM Computer Communication Review , 43: 363-374, 2013. -
- [53] R. Iyengar, J. P. Near, D. Song, O. Thakkar, A. Thakurta, and L. Wang. Towards practical differentially private convex optimization. In Conference on Computer and Communications Security , 2019. -
- [54] M. Jaggi, V. Smith, M. Takác, J. Terhorst, S. Krishnan, T. Hofmann, and M. I. Jordan. Communication-efficient distributed dual coordinate ascent. In Advances in Neural Information Processing Systems , 2014. -
- [116] S. Vaswani, F. Bach, and M. Schmidt. Fast and faster convergence of sgd for over-parameterized models (and an accelerated perceptron). In Conference on Artificial Intelligence and Statistics , 2019. -
- [118] I. Wagner and D. Eckhoff. Technical privacy metrics: a systematic survey. ACM Computing Surveys , 51:57, 2018. -
- [114] S. Thrun and L. Pratt. Learning to learn . Springer Science & Business Media, 2012. -
- [121] J. Wang and G. Joshi. Adaptive communication strategies to achieve the best error-runtime trade-off in localupdate sgd. In Conference on Systems and Machine Learning , 2019. -
- [122] S. Wang, F. Roosta-Khorasani, P. Xu, and M. W. Mahoney. Giant: Globally improved approximate newton method for distributed optimization. In Advances in Neural Information Processing Systems , 2018. -
- [125] B. Woodworth, J. Wang, A. Smith, B. McMahan, and N. Srebro. Graph oracle models, lower bounds, and gaps for parallel stochastic optimization. In Advances in Neural Information Processing Systems , 2018. -
- [126] X. Wu, F. Li, A. Kumar, K. Chaudhuri, S. Jha, and J. Naughton. Bolt-on differential privacy for scalable stochastic gradient descent-based analytics. In International Conference on Management of Data , 2017. -
- [128] T. Yang. Trading computation for communication: Distributed stochastic dual coordinate ascent. In Advances in Neural Information Processing Systems , 2013. -
- [109] R. Tandon, Q. Lei, A. G. Dimakis, and N. Karampatziakis. Gradient coding: Avoiding stragglers in distributed learning. In International Conference on Machine Learning , 2017. -
- [107] V. Smith, S. Forte, C. Ma, M. Takac, M. I. Jordan, and M. Jaggi. Cocoa: a general framework for communicationefficient distributed optimization. Journal of Machine Learning Research , 18:1-47, 2018. -
Cited by
Items 901–1,000 of 1,044
Artificial Identification: A Novel Privacy Framework for Federated Learning Based on Blockchain
Ouyang, L., Wang, F., Tian, Y., Jia, X., Qi, H., & Wang, G. (2023) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2022.3226861 · Cited by 54
“The standard FL aims to learn a united statistical model on data stored on remote devices under the constraint that device-generated data are stored and processed locally, with only intermediate updates being communicated periodically with a central cloud or sever [2].”
BackgroundA Systematic Literature Review on Client Selection in Federated Learning
Smestad, C., & Li, J. (2023) · International Conference on Evaluation and Assessment in Software Engineering (EASE) · doi:10.1145/3593434.3593438 · Cited by 59
“As the FL models are meant to be trained on smartphones and IoT devices, the expensive cost of communication must be considered by reducing the number of communication rounds and reducing the size of the transmitted messages [28].”
Federated Domain Generalization: A Secure and Robust Framework for Intelligent Fault Diagnosis
Zhao, C., & Shen, W. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3296894 · Cited by 53
“Inrecentfive years, federated learning (FL) has opened a new door to preserve data privacy, allowing multiple clients to collaboratively train machine learning models on distributed datasets while keeping data locally [12].”
BackgroundCommunication-Efficient Federated Learning for Resource-Constrained Edge Devices
Lan, G., Liu, X.-Y., Zhang, Y., & Wang, X. (2023) · IEEE Transactions on Machine Learning in Communications and Networking · doi:10.1109/tmlcn.2023.3309773 · Cited by 73
“Federated learning [2] enables multiple clients to learn a global DNN model with the training data stored locally.”
BackgroundEnsemble Federated Learning With Non-IID Data in Wireless Networks
Zhao, Z., Wang, J., Hong, W., Quek, T. Q. S., Ding, Z., & Peng, M. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3309376 · Cited by 55
“In [8], [9], and [10], federated learning has been proposed as a novel model-level collaborated learning paradigm.”
BackgroundKröger, T., Belnarsch, A., Bilfinger, P., Ratzke, W., & Lienkamp, M. (2023) · eTransportation · doi:10.1016/j.etran.2023.100294 · Cited by 51
FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentation
Chen, H., Frikha, A., Krompaß, D., Gu, J., & Tresp, V. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00447 · Cited by 76
“This simple paradigm suffers from performance degradation when there exists data heterogeneity [28, 41].”
BackgroundFederated Learning-Oriented Edge Computing Framework for the IIoT
Liu, X., Dong, X., Ning, J., & Zhao, W. (2024) · Sensors · doi:10.3390/s24134182 · Cited by 52
“In general, in federated edge learning However queue-based devices of-fl cost of the federated edge learning system can be reduced in the long term.”
BackgroundHuang, C., Li, H., Peng, W., Tang, L. C., & Ye, Z. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3433460 · Cited by 54
Wen, H., Liu, X., Lei, B., Yang, M., Cheng, X., & Chen, Z. (2024) · Applied Energy · doi:10.1016/j.apenergy.2024.124789 · Cited by 54
Dubey, P., & Kumar, M. (2024) · Computer Science Review · doi:10.1016/j.cosrev.2024.100697 · Cited by 56
Federated Learning in radiomics: A comprehensive meta-survey on medical image analysis
Raza, A., Guzzo, A., Ianni, M., Lappano, R., Zanolini, A., Maggiolini, M., & Fortino, G. (2025) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2025.108768 · Cited by 62
IoT based intelligence for proactive waste management in Quick Service Restaurants
Aytaç, K., & Korçak, Ö. (2020) · Journal of Cleaner Production · doi:10.1016/j.jclepro.2020.125401 · Cited by 56
Reputation-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
“To enable distributed learning while preserving the privacy of the users Federated Learning (FL) has emerged as a viable concept [3].”
BackgroundGhimire, B., & Rawat, D. B. (2021) · IEEE Consumer Electronics Magazine · doi:10.1109/mce.2021.3097705 · Cited by 52
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
“To explore the applications of FL, the works in Imteaj et al. (2021), Li et al. (2020), Imteaj and Amini (2019), Chen et al. (2021a) provided comprehensive summaries on FL deployed on IoT devices.”
BackgroundMethodResultPrototype Guided Federated Learning of Visual Feature RepresentationsPreprint
Michieli, U., & Özay, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.08982 · Cited by 56
“Federated Learning (FL) is a framework proposed for distributing training of machine learning models in a network of clients (devices) with local data processed only at clients [4, 24, 30, 59].”
BackgroundPrediction in Traffic Accident Duration Based on Heterogeneous Ensemble Learning
Zhao, Y., & Deng, W. (2022) · Applied Artificial Intelligence · doi:10.1080/08839514.2021.2018643 · Cited by 53
Noman, A. A., Rahaman, M., Pranto, T. H., & Rahman, R. M. (2023) · Healthcare Analytics · doi:10.1016/j.health.2023.100135 · Cited by 55
Secure Shapley Value for Cross-Silo Federated Learning
Zheng, S., Cao, Y., & Yoshikawa, M. (2023) · Proceedings of the VLDB Endowment · doi:10.14778/3587136.3587141 · Cited by 59
Slimmable Dataset Condensation
Liu, S., Ye, J., Yu, R., & Wang, X. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00366 · Cited by 66
Federated Learning in Computer Vision
Shenaj, D., Rizzoli, G., & Zanuttigh, P. (2023) · IEEE Access · doi:10.1109/access.2023.3310400 · Cited by 57
Management of Digital Twin-Driven IoT Using Federated Learning
AbdulRahman, S., Otoum, S., Bouachir, O., & Mourad, A. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2023.3310102 · Cited by 51
“This motivates the need for distributed learning paradigms, among which Federated Learning (FL) [5], [6] turned out to be a powerful weapon in this regard and in addressing the aforementioned issues.”
BackgroundRoseAgg: Robust Defense Against Targeted Collusion Attacks in Federated Learning
Yang, H., Xi, W., Shen, Y., Wu, C., & Zhao, J. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3352415 · Cited by 54
“F EDERATED learning (FL) is an emerging decentralized machine learning paradigm that facilitates model training on distributed data without the need to transfer raw data to a central server [5], [13], [16], [36].”
BackgroundFederated learning meets remote sensing
Moreno‐Álvarez, S., Paoletti, M. E., Sanchez‐Fernandez, A. J., Rico‐Gallego, J., Han, L., & Haut, J. M. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124583 · Cited by 60
Accelerating Fair Federated Learning: Adaptive Federated Adam
Ju, L., Zhang, T., Salman Zubair, T. O. O. R., & Hellander, A. (2024) · IEEE Transactions on Machine Learning in Communications and Networking · doi:10.1109/tmlcn.2024.3423648 · Cited by 57
“With increasing concerns about data security and privacy protection, federated learning has attracted much research interest [2], [3] and has been proven to work effectively in various application domains [4], [5].”
BackgroundWang, P., Yang, H., Han, G., Yu, R., Yang, L., Sun, G., Qi, H., Wei, X., & Zhang, Q. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3439696 · Cited by 54
“Furthermore, to address the challenge of knowledge sharing among heterogeneous policies, we employ federated learning (FL) [15] algorithms to aggregate the SPN parameters of multiple UAVs, which allows learning similar navigation policy from other SPN parameters.”
MethodA scalable blockchain-enabled federated learning architecture for edge computing
Ren, S., Kim, E., & Lee, C. (2024) · PLoS ONE · doi:10.1371/journal.pone.0308991 · Cited by 54
State-of-the-Art Security Schemes for the Internet of Underwater Things: A Holistic Survey
Adam, N. H., Ali, M., Naeem, F., Ghazy, A. S., & Kaddoum, G. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3474290 · Cited by 55
“Applications for FL are being found in several privacy-sensitive sectors that rely on distributed data storage [129].”
BackgroundA Comprehensive Review and Assessment of Cybersecurity Vulnerability Detection Methodologies
Bennouk, K., Aali, N. A., Idrissi, Y. E. B. E., Sebai, B., Faroukhi, A. Z., & Mahouachi, D. (2024) · Journal of Cybersecurity and Privacy · doi:10.3390/jcp4040040 · Cited by 58
Federated Offline Reinforcement Learning with Proximal Policy Evaluation
Yue, S., Deng, Y., Wang, G. Y., Ren, J., & Zhang, Y. (2024) · Chinese Journal of Electronics · doi:10.23919/cje.2023.00.288 · Cited by 54
Pratihar, R., & Sankar, R. T. (2024) · Computers · doi:10.3390/computers13110293 · Cited by 53
Sugunaraj, N., Balaji, S. R. A., Chandar, B. S., Rajagopalan, P., Köse, U., Loper, D. C., Mahfuz, T., Chakraborty, P., Ahmad, S., Kim, T., et al. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3534828 · Cited by 65
A dynamic barycenter bridging network for federated transfer fault diagnosis in machine groups
Yang, B., Lei, Y., Li, X., Li, N., Si, X., & Chen, C. (2025) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2025.112605 · Cited by 49
Quality-aware user recruitment based on federated learning in mobile crowd sensing
Zhang, W., Li, Z., & Chen, X. (2021) · Tsinghua Science & Technology · doi:10.26599/tst.2020.9010046 · Cited by 48
Federated Learning for Privacy-Preserved Medical Internet of Things
Thilakarathne, N. N., Muneeswari, G., Parthasarathy, V., Alassery, F., Hamam, H., Mahendran, R. K., & Shafiq, M. (2022) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2022.023763 · Cited by 56
Joint Optimal Quantization and Aggregation of Federated Learning Scheme in VANETs
Li, Y., Guo, Y., Alazab, M., Chen, S., Shen, C., & Yu, K. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3145823 · Cited by 52
“Even though only local models are transferred, communication might be still one of the key bottlenecks for FL [5], [6].”
BackgroundToward Federated-Learning-Enabled Visible Light Communication in 6G Systems
Naser, S. A., Bariah, L., Muhaidat, S., Sofotasios, P. C., Al‐Qutayri, M., Damiani, E., & Debbah, M. A. (2022) · IEEE Wireless Communications · doi:10.1109/mwc.005.00334 · Cited by 48
Federated Learning via Over-the-Air Computation With Statistical Channel State Information
Jing, S., & Xiao, C. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3175887 · Cited by 51
“Though the behavior of FL has been well studied, especially its convergence under data heterogeneity and stochastic gradient variance [6][7][8], the impacts of communication channels between clients and the server are often ignored [9][10].”
BackgroundTerahertz-Band Channel and Beam Split Estimation via Array Perturbation Model
Elbir, A. M., Shi, W., Papazafeiropoulos, A., Kourtessis, P., & Chatzinotas, S. (2023) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2023.3263625 · Cited by 48
“Similar to the previous works, the communication overhead is defined as the amount of transmitted data during model training [54, 56, 57].”
ResultFederated Noisy Client Learning
Tam, K., Li, L., Han, B., Xu, C., & Fu, H. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3336050 · Cited by 61
“To ensure data privacy in the learning procedure, federated learning (FL) was recently proposed as a workflow that enables local clients to collaboratively train a shared global model without sharing local private data [15, 39, 17, 14].”
Zheng, J., Tian, H., Ni, W., Ni, W., & Zhang, P. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3188502 · Cited by 47
“FL requires locally trained models to be aggregated periodically, to create the global model [5], [6].”
BackgroundRajendran, S., Pan, W., Sabuncu, M. R., Chen, Y., Zhou, J., & Wang, F. (2024) · Patterns · doi:10.1016/j.patter.2023.100913 · Cited by 47
A Review of Client Selection Methods in Federated Learning
Mayhoub, S., & M. Shami, T. (2024) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-023-10011-4 · Cited by 47
“Although some papers argue that it is possible to infer private information about clients from their updated local models [10, 19, 60].”
InfluentialEdge Learning: The Enabling Technology for Distributed Big Data Analytics in the Edge
Zhang, J., Qu, Z., Chen, C., Wang, H., Zhan, Y., Ye, B., & Guo, S. (2021) · ACM Computing Surveys · doi:10.1145/3464419 · Cited by 83
“It allows users to collab-oratively train a shared model while keeping personal data in local without any privacy leakage [64, 68, 88, 136].”
BackgroundDistributed Learning for Wireless Communications: Methods, Applications and Challenges
Qian, L., Yang, P., Xiao, M., Dobre, O. A., Renzo, M. D., Li, J., Han, Z., Qin, Y., & Zhao, J. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3156756 · Cited by 60
Privacy-preserving Speech Emotion Recognition through Semi-Supervised Federated Learning
Tsouvalas, V., Özçelebi, T., & Meratnia, N. (2022) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops53856.2022.9767445 · Cited by 68
“significant challenges during training [13], being unrestrained by those challenges is yet another reason to learn federated SER models and build privacy-preserving systems.”
BackgroundArtificial Intelligence (AI) and Machine Learning for Multimedia and Edge Information Processing
Seng, J. K. P., Ang, K. L.-M., Peter, E., & Mmonyi, A. C. (2022) · Electronics · doi:10.3390/electronics11142239 · Cited by 55
de Hond, A. A. H., Kant, I. M. J., Fornasa, M., Cinà, G., Elbers, P. W. G., Thoral, P. J., Sesmu Arbous, M., & Steyerberg, E. W. (2023) · Critical Care Medicine · doi:10.1097/ccm.0000000000005758 · Cited by 44
“Alternatively, up and coming techniques such as federated learning may prove useful in addressing the generalizability issue (35, 36).”
BackgroundMachine Learning C–N Couplings: Obstacles for a General-Purpose Reaction Yield Prediction
Fitzner, M., Wuitschik, G., Koller, R., Adam, J., & Schindler, T. (2023) · ACS Omega · doi:10.1021/acsomega.2c05546 · Cited by 49
Du, J., Qin, N., Huang, D., Zhang, Y., & Jia, X. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3238724 · Cited by 55
“…due to the potential conflicts of interest in the industries, the consideration of users for the security of private information, and the lack of enterprise-related technologies, it is still difficult to effectively and safely realize the cooperation and exchange of multiclient data [13], [14].”
BackgroundZhang, X., Zhang, B., Yu, W., & Kang, X. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3244136 · Cited by 63
“To circumvent these challenges, federated learning, a typical multiagent distributed learning framework, has been proposed to train a shared prediction model using data distributed among multiple clients while keeping the private data of clients confidential [14], [15].”
Joint Device Scheduling and Bandwidth Allocation for Federated Learning Over Wireless Networks
Zhang, T., Lam, K., Zhao, J., & Feng, J. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3291701 · Cited by 56
“Although FL has the potential to attain remarkable improvements, it is challenging to implement FL in practical wireless networks [12].”
Shao, J., Li, Z., Sun, W., Zhou, T., Sun, Y., Liu, L., Lin, Z., Mao, Y., & Zhang, J. (2026) · ACM Computing Surveys · doi:10.1145/3844940 · Cited by 56
“Section 2 first introduces the basic concepts of FL and privacy threats.”
Falcon: A Privacy-Preserving and Interpretable Vertical Federated Learning System
Wu, Y., Xing, N., Chen, G., Dinh, T. T. A., Luo, Z., Ooi, B. C., Xiao, X., & Zhang, M. (2023) · Proceedings of the VLDB Endowment · doi:10.14778/3603581.3603588 · Cited by 61
“Federated learning (FL) [8, 23, 29, 39, 40, 42, 44, 50, 68, 75] enables collaborations among multiple parties, as it provides a framework with which the parties can jointly build machine learning [47, 49, 58] (ML) models from their combined datasets.”
BackgroundSource Inference Attacks: Beyond Membership Inference Attacks in Federated Learning
Hu, H., Zhang, X., Salcic, Z. A., Sun, L., Choo, K. R., & Dobbie, G. (2023) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2023.3321565 · Cited by 66
“Many recent works [29], [31], [45], [47], [57] have shown that the non-IID data distribution has brought important challenges to FL such There are several promising applications where SIAs can be applied.”
BackgroundHan, D.-J., Kim, D.-Y., Choi, M., Nickel, D., Moon, J. J., Chiang, M., & Brinton, C. G. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2023.3331690 · Cited by 53
“Federatedlearning (FL)[2],[3],[4],themostrecentlypopularizedtechniquefor distributingMLacrossedgedevices,hasdemonstratedasharp tradeoffbetweentheseobjectives.”
Multi-Stage Asynchronous Federated Learning With Adaptive Differential Privacy
Li, Y., Yang, S., Ren, X., Shi, L., & Zhao, C. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3332428 · Cited by 55
“However, FL faces several core challenges in addressing the distributed optimization problem, like system heterogeneity, privacy concerns, expensive communication and statistical heterogeneity [7].”
BackgroundZhao, C., & Shen, W. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107765 · Cited by 47
Popli, M. S., Singh, R. P., Popli, N. K., & Mamun, M. (2025) · IEEE Access · doi:10.1109/access.2025.3530499 · Cited by 55
Network Digital Twin Toward Networking, Telecommunications, and Traffic Engineering: A Survey
Poorzare, R., Kanellopoulos, D. N., Sharma, V. K., Dalapati, P., & Waldhorst, O. P. (2025) · IEEE Access · doi:10.1109/access.2025.3531947 · Cited by 62
Using Federated Learning on Malware Classification
Lin, K.-Y., & Huang, W.-R. (2020) · International Conference on Advanced Communication Technology · doi:10.23919/icact48636.2020.9061261 · Cited by 47
“In [12] Li et al. showed that Federated learning can be classified into two categories: global privacy and local privacy.”
BackgroundThe Societal Implications of Deep Reinforcement Learning
Whittlestone, J., Arulkumaran, K., & Crosby, M. (2021) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.12360 · Cited by 66
“…is ongoing technical work in areas such as federated learning and differential privacy attempting to address some of these issues (Ji et al., 2014; Li et al., 2020), and the European Union’s General Data Protection Regulation (GDPR) represents an important legislative step towards protecting…”
BackgroundPersonalized Retrogress-Resilient Framework for Real-World Medical Federated Learning
Chen, Z., Zhu, M., Yang, C., & Yuan, Y. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87199-4_33 · Cited by 61
“this challenge, Federated Learning (FL) [8,17] provides a collaborative paradigm to optimize local models at multiple clients, and regularly aggregate these local models together at a global server.”
BackgroundA Review of Emotion Recognition Methods From Keystroke, Mouse, and Touchscreen Dynamics
Yang, L., & Qin, S. (2021) · IEEE Access · doi:10.1109/access.2021.3132233 · Cited by 61
“As the development of hardware performance, the computers, mobile phones and wearable devices have growing computational power, so it is increasingly attractive to store and compute emotion related data locally [113].”
BackgroundNasser, N., Fadlullah, Z. M., Fouda, M. M., Ali, A., & Imran, M. A. (2021) · Computer Networks · doi:10.1016/j.comnet.2021.108672 · Cited by 47
What Do We Mean by Generalization in Federated Learning?Preprint
Yuan, H., Morningstar, W. R., Ning, L., & Singhal, K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.14216 · Cited by 88
“In cross-device FL settings, clients are sampled from a population for participation in each round of training (Kairouz et al., 2019; Li et al., 2020a).”
BackgroundOn-device machine learning An algorithms and learning theory perspective
Dhar, S., Guo, J., Liu, J., Tripathi, S., Kurup, U., & Shah, M. (2019) · arXiv · doi:10.48550/arxiv.1911.00623 · Cited by 47
Adam, M., & Baroudi, U. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3506214 · Cited by 46
Mu, Y., Garg, N., & Ratnarajah, T. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3196463 · Cited by 49
“With its privacy-preserving nature, FL has been recognized as one of the most promising solutions to resolve and fulfill the challenges in 6G communication networks [12].”
BackgroundFedGAMMA: Federated Learning With Global Sharpness-Aware Minimization
Dai, R., Yang, X., Sun, Y., Shen, L., Tian, X., Wang, M., & Zhang, Y. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3304453 · Cited by 60
“In response, federated learning (FL) emerged as a decentralized machine learning framework that enables multiple entities to jointly train a global model with privacy protections [9], [10], [11], [12], [13], [14].”
Labeling Chaos to Learning Harmony: Federated Learning with Noisy Labels
Tsouvalas, V., Saeed, A., Özçelebi, T., & Meratnia, N. (2023) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3626242 · Cited by 56
“However, the rapidly increasing volume of generated data, combined with high communication costs and bandwidth limitations, makes centralized data aggregation infeasible [22].”
BackgroundRPIFL: Reliable and Privacy-Preserving Federated Learning for the Internet of Things
Wang, R., Lai, J., Li, X., He, D., & Khan, M. K. (2023) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2023.103768 · Cited by 50
FedSL: A Communication-Efficient Federated Learning With Split Layer Aggregation
Zhang, W., Zhou, T., Lu, Q., Yuan, Y., Tolba, A. K. R., & Said, W. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3350241 · Cited by 53
“Existing works [7], [8] FL has primarily focused on federated optimization, FL algorithms, privacy mechanisms [13], heterogeneity data [14], attacks systems [15], [16], communication costs, etc. McMahan et al. [5] proposed FedAvg, an algorithm that averages local models from remote devices to learn…”
BackgroundMethodA review on client-server attacks and defenses in federated learning
Sharma, A., & Marchang, N. (2024) · Computers & Security · doi:10.1016/j.cose.2024.103801 · Cited by 56
Non-Gaussian normative modelling with hierarchical Bayesian regression
de Boer, A. A. A., Bayer, J., Kia, S. M., Rutherford, S. E., Zabihi, M., Fraza, C., Barkema, P., Westlye, L. T., Andreassen, O. A., Hinne, M., et al. (2024) · Imaging Neuroscience · doi:10.1162/imag_a_00132 · Cited by 54
“This requires federated learning; a distributed learning approach that does not require transportation of the data, only of the inferred parameters of model ( Kia et al., 2021; Li et al., 2020).”
BackgroundError-Aware Conversion from ANN to SNN via Post-training Parameter Calibration
Li, Y., Deng, S., Dong, X., & Gu, S. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02046-2 · Cited by 60
“Federated Learning (Li et al., 2020) satisfies this goal by uploading the model parameters to the server rather than the data, resulting in decentralized optimization .”
InfluentialValdez, W., Parra-Ullauri, J. M., & Kertész, A. (2024) · IEEE Access · doi:10.1109/access.2024.3398034 · Cited by 53
“Such situations often occur in real-world contexts due to variations in data sources or devices [55], [56].”
BackgroundMulti-Level Personalized Federated Learning on Heterogeneous and Long-Tailed Data
Zhang, R., Chen, Y. F., Wu, C., Wang, F., & Li, B. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3409159 · Cited by 57
“This technique [14], [15], [16], [17] facilitates collaborative training across clients while preserving data confidentiality.”
BackgroundGupta, A., Maurya, M. K., Dhere, K., & Chaurasiya, V. K. (2024) · IEEE Access · doi:10.1109/access.2024.3464240 · Cited by 50
The Metaverse for Industry 5.0 in NextG Communications: Potential Applications and Future Challenges
Prabadevi, B., Deepa, N., Maddikunta, P. K. R., Victor, N., Gadekallu, T. R., Yenduri, G., Wang, W. W., Pham, Q., Huynh‐The, T., & Liyanage, M. (2024) · IEEE Open Journal of the Computer Society · doi:10.1109/ojcs.2024.3497335 · Cited by 52
“Therefore, FL will ensure continual learning without data breaches due to private data aggregation and reduce the communication overhead [119], specifically for the larger models of complex scenarios with massive data [120].”
Hoang, M. L. (2025) · IEEE Access · doi:10.1109/access.2025.3573937 · Cited by 52
Graph Neural Networks for Next-Generation-IoT: Recent Advances and Open Challenges
Tung, N. X., Giang, L. T., Son, B. D., Geun-Jeong, S., Chien, T. V., Hanzo, L., & Hwang, W.-J. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3613845 · Cited by 66
“FL allows multiple edge devices to collaboratively train a shared model without exchanging raw data, preserving privacy and reducing communication overhead [183], [184], [185], [186], [187], [188], [189].”
A Systematic Literature Review on Federated Learning: From A Model Quality Perspective
Liu, Y., Zhang, L., Ge, N., & Li, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.01973 · Cited by 50
“• The literature [6] discusses the four challenges in FL: expensive learning, system heterogeneity, statistical heterogeneity, and privacy issues.”
BackgroundEnd-to-End Speech Recognition from Federated Acoustic Models
Gao, Y., Parcollet, T., Zaiem, S., Fernández-Marqués, J., de Gusmão, P. P. B., Beutel, D. J., & Lane, N. D. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747161 · Cited by 68
Peyvandi, A., Majidi, B., Peyvandi, S., & Patra, J. C. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12900-5 · Cited by 52
“A decentralized solution for training machine learning models is federated learning [38].”
BackgroundA Study on Multi-Antenna and Pertinent Technologies with AI/ML Approaches for B5G/6G Networks
Siddiqui, M. U. A., Qamar, F., Kazmi, S. H. A., Hassan, R. B., Arfeen, A., & Nguyễn, Q. N. (2022) · Electronics · doi:10.3390/electronics12010189 · Cited by 48
Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-SharingPreprint
Khodak, M., Tu, R., Li, T., Li, L., Balcan, M.-F., Smith, V., & Talwalkar, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.04502 · Cited by 106
“Federated learning (FL) is a popular distributed computational setting where training is performed locally or privately [30, 36] and where hyperparameter tuning has been identified as a critical problem [18].”
BackgroundSelf-citationPrivacy-Enhanced Decentralized Federated Learning at Dynamic Edge
Chen, S., Wang, Y., Yu, D., Ren, J., Xu, C., & Zheng, Y. (2023) · IEEE Transactions on Computers · doi:10.1109/tc.2023.3239542 · Cited by 48
“Thus, the decentralized FL architecture without the special aid of a PS has been proposed [7], [8], [9], [23].”
BackgroundChen, J., Chen, S., Wee, L., Dekker, A. L. A. J., & Bermejo, I. (2023) · Physics in Medicine and Biology · doi:10.1088/1361-6560/acba74 · Cited by 52
“…29.9± 4.94 — 30.7± 1.36 0.85± 0.03 Maspero et al (2020) CBCT-CT 69S 30S 51± 12 — — — Huang et al (2020) PD-T2 230S 118S 37.0 — — 0.96 Li et al (2020b) CT-MR 28S 6S 88.7± 7.86 — 30.9± 0.62 0.92± 0.01 Li et al (2020c) CT-MR 28S 6S 88.7± 10.0 — 30.8± 0.73 0.92± 0.01 Oda et al (2019) Vir-real EP…”
BackgroundMethodInfluentialFederated Learning Over Wireless Networks: Challenges and Solutions
Beitollahi, M., & Lu, N. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3285868 · Cited by 51
“However, there are many other proposed aggregation methods in the literature, including FedProx [17], SCAFFOLD [18], FedAWS [19], FedAdam [20], and FedPer [21].”
MethodFederated Learning in Heterogeneous Networks With Unreliable Communication
Zheng, P., Zhu, Y. L., Hu, Y., Zhang, Z. J., & Schmeink, A. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3311824 · Cited by 52
“Due to its highly distributed nature, one of the major challenges in FL is to address the heterogeneity [5], [6].”
BackgroundGoh, E., Kim, D., Lee, K., Oh, S., Chae, J.-E., & Kim, D.-Y. (2023) · IEEE Access · doi:10.1109/access.2023.3345360 · Cited by 53
“As a result, it can significantly reduce server resource usage and ensure data privacy [6], [15]–[17].”
BackgroundCross-Modal Vertical Federated Learning for MRI Reconstruction
Yan, Y., Wang, H., Huang, Y., He, N., Zhu, L., Xu, Y. D., Li, Y., & Zheng, Y. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3360720 · Cited by 57
“Federated learning (FL), an attractive distributed learning paradigm, which allows multiple institutions to cooperate on the premise of protecting privacy [5], [6], [7], has been adopted to solve the aforementioned problems [8].”
BackgroundSecurity, privacy, and robustness for trustworthy AI systems: A review
Saeed, M. M., & Alsharidah, M. (2024) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2024.109643 · Cited by 54
Gradient Compression and Correlation Driven Federated Learning for Wireless Traffic Prediction
Zhang, C., Zhang, H., Dang, S., Shihada, B., & Alouini, M. (2024) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2024.3524183 · Cited by 51
“Thanks to the advancement of distributed machine learning, particularly federated learning (FL) [24], [25], [26], [27], [28], [29], [30], [31], [32], [33], both model training and prediction can be performed at the edge.”
Federated Learning in Practice: Reflections and Projections
Daly, K., Eichner, H., Kairouz, P., McMahan, H. B., Ramage, D., & Xu, Z. (2024) · IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA) · doi:10.1109/tps-isa62245.2024.00026 · Cited by 70
“Both FL and FA have made remarkable progress in theory and practice in recent years [25, 42, 45, 65, 69, 78].”
DeSMP: Differential Privacy-exploited Stealthy Model Poisoning Attacks in Federated Learning
Hossain, M. T., Islam, S., Badsha, S., & Shen, H. (2021) · 2021 17th International Conference on Mobility, Sensing and Networking (MSN) · doi:10.1109/msn53354.2021.00038 · Cited by 44
Federated learning architecture: Design, implementation, and challenges in distributed AI systems
Shanmugam, L., Tillu, R., & Tomar, M. (2023) · Journal of Knowledge Learning and Science Technology ISSN: 2959-6386 (online) · doi:10.60087/jklst.vol2.n2.p384 · Cited by 42
“Additionally, in-cluster training and gradient scarification techniques improve communication efficiency and performance, especially with Non-IID data, as demonstrated by the FedOES approach [3] .”
BackgroundMethodSlow and Stale Gradients Can Win the Race
Dutta, S., Wang, J., & Joshi, G. (2021) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2021.3103770 · Cited by 40
Metadata
- Authors
- Li, T., Sahu, A. K., Talwalkar, A., & Smith, V.
- Affiliations
- Carnegie Mellon University (US)
- ORCID
- Sahu, Anit Kumar
- Venue
- IEEE Signal Processing Magazine
- Published
- 2020-05
- Volume
- 37
- Issue
- 3
- Pages
- 50-60
- ISSN
- 1053-5888 (ISSN-L)
- 1558-0792
- OpenAlex
- W3021654819
- Cited by
- 6,210
- References
- 53
- Citations by year
- 2026: 955 · 2025: 1259 · 2024: 1180 · 2023: 1143 · 2022: 789 · 2021: 624 · 2020: 233
- FWCI
- 274.11
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Signal Processing Magazine (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- federated learning, data localization, privacy-preserving machine learning, distributed optimization, heterogeneous networks, large-scale machine learning, mobile devices
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.