mlsanityData to 7 Oct 2026

Multiplayer Federated Learning: Reaching Equilibrium with Less Communication

arXiv 2501.08263 ↗First posted 14 Jan 2025cs.LG math.OC stat.MLcited by 5

Not on the map. Why?

Abstract (arXiv)

Traditional Federated Learning (FL) approaches assume collaborative clients with aligned objectives working towards a shared global model. However, in many real-world scenarios, clients act as rational players with individual objectives and strategic behaviors, a concept that existing FL frameworks are not equipped to adequately address. To bridge this gap, we introduce Multiplayer Federated Learning (MpFL), a novel framework that models the clients in the FL environment as players in a game-theoretic context, aiming to reach an equilibrium. In this scenario, each player tries to optimize their own utility function, which may not align with the collective goal. Within MpFL, we propose Per-Player Local Stochastic Gradient Descent (PEARL-SGD), an algorithm in which each player/client performs local updates independently and periodically communicates with other players. We theoretically analyze PEARL-SGD and prove that it reaches a neighborhood of equilibrium with less communication in the stochastic setup compared to its non-local counterpart. Finally, we verify our theoretical findings through numerical experiments.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 94 of its 149 references that are in the map. First posted on arXiv 14 Jan 2025.

Builds on

94 of 149 references.

References · 94

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  5. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  6. 2018Federated Learning with Non-IID Datacited by 1,099
  7. 2017Federated Multi-Task Learningcited by 669
  8. 2020Personalized Federated Learning with Moreau Envelopescited by 612
  9. 2018Local SGD Converges Fast and Communicates Littlecited by 595
  10. 2018Federated Learning for Mobile Keyboard Predictioncited by 565
  11. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  12. 2021Towards Personalized Federated Learningcited by 462
38 more
  1. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 408
  2. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 371
  3. 2020A Unified Theory of Decentralized SGD with Changing Topology and Local Updatescited by 361
  4. 2020Adaptive Personalized Federated Learningcited by 353
  5. 2018Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learningcited by 277
  6. 2019On Gradient Descent Ascent for Nonconvex-Concave Minimax Problemscited by 266
  7. 2019Tighter Theory for Local SGD on Identical and Heterogeneous Datacited by 266
  8. 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 265
  9. 2017Training GANs with Optimismcited by 217
  10. 2020Federated Learning of a Mixture of Global and Local Modelscited by 208
  11. 2019SGD: General Analysis and Improved Ratescited by 206
  12. 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 189
  13. 2013Optimization, Learning, and Games with Predictable Sequencescited by 187
  14. 2019Adaptive Gradient-Based Meta-Learning Methodscited by 183
  15. 2019On the Convergence of Local Descent Methods in Federated Learningcited by 150
  16. 2016Achieving Geometric Convergence for Distributed Optimization over Time-Varying Graphscited by 149
  17. 2018A Variational Inequality Perspective on Generative Adversarial Networkscited by 144
  18. 2019A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approachcited by 142
  19. 2022ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!cited by 134
  20. 2020Lower Bounds and Optimal Algorithms for Personalized Federated Learningcited by 122
  21. 2021Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradientscited by 122
  22. 2020FedVision: An Online Visual Object Detection Platform Powered by Federated Learningcited by 121
  23. 2017The Numerics of GANscited by 104
  24. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 104
  25. 2018The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimizationcited by 98
  26. 2020Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimizationcited by 94
  27. 2020Local SGD: Unified Theory and New Efficient Methodscited by 88
  28. 2016Learning in games with continuous action sets and unknown payoff functionscited by 78
  29. 2021Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with O(1/k2) Rate on Squared Gradient Normcited by 71
  30. 2020SGD for Structured Nonconvex Functions: Learning Rates, Minibatching and Interpolationcited by 66
  31. 2022A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Gamescited by 64
  32. 2019Reducing Noise in GAN Training with Variance Reduced Extragradientcited by 61
  33. 2021Fast Extra Gradient Methods for Smooth Structured Nonconvex-Nonconcave Minimax Problemscited by 61
  34. 2020Halpern Iteration for Near-Optimal and Parameter-Free Monotone Inclusion and Strong Solutions to Variational Inequalitiescited by 60
  35. 2020Model-sharing Games: Analyzing Federated Learning Under Voluntary Participationcited by 60
  36. 2022FedNest: Federated Bilevel, Minimax, and Compositional Optimizationcited by 60
  37. 2020Multi-Task Federated Learning for Personalised Deep Neural Networks in Edge Computingcited by 52
  38. 2020The limits of min-max optimization algorithms: convergence to spurious non-critical setscited by 50

50 most cited of 94 All 94 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 1.

5 papers.

  1. 2025Incentivizing Truthful Language Models via Peer Elicitation Gamescited by 8
  2. 2025Extragradient Method for (L0, L1)-Lipschitz Root-finding Problemscited by 3
  3. 2026Direct Acceleration of Stochastic Root-Finding Without Variance Reduction and Regularizationcited by 3
  4. 2025Online Federation For Mixtures of Proprietary Agents with Black-Box Encoderscited by 1
  5. 2025Decoupled SGDA for Games with Intermittent Strategy Communicationcited by 0