mlsanityData to 14 Oct 2026

Game of Gradients: Mitigating Irrelevant Clients in Federated Learning

arXiv 2110.12257 ↗First posted 23 Oct 2021cs.LG cs.AI cs.DCcited by 35

Not on the map. Why?

Abstract (arXiv)

The paradigm of Federated learning (FL) deals with multiple clients participating in collaborative training of a machine learning model under the orchestration of a central server. In this setup, each client's data is private to itself and is not transferable to other clients or the server. Though FL paradigm has received significant interest recently from the research community, the problem of selecting the relevant clients w.r.t. the central server's learning objective is under-explored. We refer to these problems as Federated Relevant Client Selection (FRCS). Because the server doesn't have explicit control over the nature of data possessed by each client, the problem of selecting relevant clients is significantly complex in FL settings. In this paper, we resolve important and related FRCS problems viz., selecting clients with relevant data, detecting clients that possess data relevant to a particular target label, and rectifying corrupted data samples of individual clients. We follow a principled approach to address the above FRCS problems and develop a new federated learning method using the Shapley value concept from cooperative game theory. Towards this end, we propose a cooperative game involving the gradients shared by the clients. Using this game, we compute Shapley values of clients and then present Shapley value based Federated Averaging (S-FedAvg) algorithm that empowers the server to select relevant clients with high probability. S-FedAvg turns out to be critical in designing specific algorithms to address the FRCS problems. We finally conduct a thorough empirical analysis on image classification and speech recognition tasks to show the superior performance of S-FedAvg than the baselines in the context of supervised federated learning settings.

Key facts. Cited by 35 papers in the map (data through 14 Oct 2026). Builds on 17 of its 32 references that are in the map. First posted on arXiv 23 Oct 2021.

Builds on

17 of 32 references.

References · 17

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2016Deep Learning with Differential Privacycited by 2,728
  3. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  4. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  5. 2018Federated Learning with Non-IID Datacited by 1,108
  6. 2019Deep Leakage from Gradientscited by 1,021
  7. 2019Towards Federated Learning at Scale: System Designcited by 832
  8. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 665
  9. 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 629
  10. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  11. 2019Federated Machine Learning: Concept and Applicationscited by 412
  12. 2020Classification-Based Anomaly Detection for General Datacited by 211
5 more
  1. 2019On the Convergence of Local Descent Methods in Federated Learningcited by 153
  2. 2018Iterative Learning with Open-set Noisy Labelscited by 108
  3. 2016CoCoA: A General Framework for Communication-Efficient Distributed Optimizationcited by 69
  4. 2019Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approachcited by 45
  5. 2018Task Agnostic Robust Learning on Corrupt Outputs by Correlation-Guided Mixture Density Networkscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 7; 2023: 8; 2024: 11; 2025: 7; 2026: 1.

35 papers.

Sort:

  1. 2022A Survey on Heterogeneous Federated Learningcited by 42
  2. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 41
  3. 2024Advances and Open Challenges in Federated Foundation Modelscited by 36
  4. 2022FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Servercited by 29
  5. 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
  6. 2022Minimax Demographic Group Fairness in Federated Learningcited by 24
  7. 2021An Efficient Federated Distillation Learning System for Multi-task Time Series Classificationcited by 14
  8. 2023Towards Interpretable Federated Learningcited by 11
  9. 2022A Snapshot of the Frontiers of Client Selection in Federated Learningcited by 9
  10. 2023Fair yet Asymptotically Equal Collaborative Learningcited by 8
  11. 2024A Comprehensive Survey of Federated Transfer Learning: Challenges, Methods and Applicationscited by 8
  12. 2022Long-Short History of Gradients is All You Need: Detecting Malicious and Unreliable Clients in Federated Learningcited by 7
23 more
  1. 2023Greedy Shapley Client Selection for Communication-Efficient Federated Learningcited by 7
  2. 2022Learnings from Federated Learning in the Real worldcited by 6
  3. 2024Gradient Coreset for Federated Learningcited by 6
  4. 2024Efficient Federated Learning Using Dynamic Update and Adaptive Pruning with Momentum on Shared Server Datacited by 6
  5. 2023Mitigating Group Bias in Federated Learning for Heterogeneous Devicescited by 5
  6. 2022Robust Federated Learning against both Data Heterogeneity and Poisoning Attack via Aggregation Optimizationcited by 3
  7. 2023Exploring Data Redundancy in Real-world Image Classification through Data Selectioncited by 3
  8. 2024Maverick-Aware Shapley Valuation for Client Selection in Federated Learningcited by 2
  9. 2024A Comprehensive Study of Shapley Value in Data Analyticscited by 2
  10. 2023Using Cooperative Game Theory to Prune Neural Networkscited by 1
  11. 2024ROSS: RObust decentralized Stochastic learning based on Shapley valuescited by 1
  12. 2024FLMarket: Enabling Privacy-preserved Pre-training Data Pricing for Federated Learningcited by 1
  13. 2025FedABC: Attention-Based Client Selection for Federated Learning with Long-Term Viewcited by 1
  14. 2024Auditable Homomorphic-based Decentralized Collaborative AI with Attribute-based Differential Privacycited by 0
  15. 2024GPFL: A Gradient Projection-Based Client Selection Framework for Efficient Federated Learningcited by 0
  16. 2024CoAst: Validation-Free Contribution Assessment for Federated Learning based on Cross-Round Valuationcited by 0
  17. 2025Data Overvaluation Attack and Truthful Data Valuation in Federated Learningcited by 0
  18. 2025Decoding FL Defenses: Systemization, Pitfalls, and Remediescited by 0
  19. 2025Tackling Heterogeneity in Federated Learning via Variance-Reduced Boltzmann Sampling within Homogeneous Social Coalitionscited by 0
  20. 2025Owen Sampling Accelerates Contribution Estimation in Federated Learningcited by 0
  21. 2025Gaming and Cooperation in Federated Learning: What Can Happen and How to Monitor Itcited by 0
  22. 2025Semi-overlapping Multi-bandit Best Arm Identification for Sequential Support Network Learningcited by 0
  23. 2026Meritocratic Fairness via K-Shapley Values in Budgeted Combinatorial Bandits with Full-Bandit Feedbackcited by 0