mlsanityData to 14 Oct 2026

One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning

arXiv 2103.03228 ↗First posted 4 Mar 2021cs.LG cs.DS cs.GTcited by 39

Not on the map. Why?

Abstract (arXiv)

In recent years, federated learning has been embraced as an approach for bringing about collaboration across large populations of learning agents. However, little is known about how collaboration protocols should take agents' incentives into account when allocating individual resources for communal learning in order to maintain such collaborations. Inspired by game theoretic notions, this paper introduces a framework for incentive-aware learning and data sharing in federated learning. Our stable and envy-free equilibria capture notions of collaboration in the presence of agents interested in meeting their learning objectives while keeping their own sample collection burden low. For example, in an envy-free equilibrium, no agent would wish to swap their sampling burden with any other agent and in a stable equilibrium, no agent would wish to unilaterally reduce their sampling burden. In addition to formalizing this framework, our contributions include characterizing the structural properties of such equilibria, proving when they exist, and showing how they can be computed. Furthermore, we compare the sample complexity of incentive-aware collaboration with that of optimal collaboration when one ignores agents' incentives.

Key facts. Cited by 39 papers in the map (data through 14 Oct 2026). Builds on 15 of its 32 references that are in the map. First posted on arXiv 4 Mar 2021.

Builds on

15 of 32 references.

References · 15

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 629
  4. 2019Fair Resource Allocation in Federated Learningcited by 394
  5. 2019Towards Efficient Data Valuation Based on the Shapley Valuecited by 281
  6. 2017EMNIST: an extension of MNIST to handwritten letterscited by 213
  7. 2020Collaborative Fairness in Federated Learningcited by 95
  8. 2018A Marketplace for Data: An Algorithmic Solutioncited by 76
  9. 2020Collaborative Machine Learning with Incentive-Aware Model Rewardscited by 71
  10. 2020Model-sharing Games: Analyzing Federated Learning Under Voluntary Participationcited by 60
  11. 2019Free-riders in Federated Learning: Attacks and Defensescited by 49
  12. 2020Hierarchically Fair Federated Learningcited by 28
3 more
  1. 2018Improved Algorithms for Collaborative PAC Learningcited by 20
  2. 2018Tight Bounds for Collaborative PAC Learning via Multiplicative Weightscited by 15
  3. 2017Statistical Cost Sharingcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 5; 2023: 12; 2024: 8; 2025: 7; 2026: 5.

39 papers.

Sort:

By area:

  1. 2021Optimality and Stability in Federated Learning: A Game-theoretic Approachcited by 40
  2. 2022On-Demand Sampling: Learning Optimally from Multiple Distributionscited by 39
  3. 2022Anchor Sampling for Federated Learning with Partial Client Participationcited by 14
  4. 2023Optimal Multi-Distribution Learningcited by 13
  5. 2023The sample complexity of multi-distribution learningcited by 12
  6. 2021Models of fairness in federated learningcited by 8
  7. 2023Fair yet Asymptotically Equal Collaborative Learningcited by 8
  8. 2022A Fair Federated Learning Framework With Reinforcement Learningcited by 6
  9. 2023Strategic Data Sharing between Competitorscited by 6
  10. 2023Scaff-PD: Communication Efficient Fair and Robust Federated Learningcited by 6
  11. 2023On the Effect of Defections in Federated Learning and How to Prevent Themcited by 5
  12. 2025Multiplayer Federated Learning: Reaching Equilibrium with Less Communicationcited by 5
27 more
  1. 2023Probably Approximately Correct Federated Learningcited by 4
  2. 2024Collaborative Mean Estimation Among Heterogeneous Strategic Agents: Individual Rationality, Fairness, and Truthful Contributioncited by 4
  3. 2022Maximizing Global Model Appeal in Federated Learningcited by 3
  4. 2024FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?cited by 3
  5. 2024Incentivizing Truthful Collaboration in Heterogeneous Federated Learningcited by 3
  6. 2025The Backfiring Effect of Weak AI Safety Regulationcited by 3
  7. 2024How to Collaborate: Towards Maximizing the Generalization Performance in Cross-Silo Federated Learningcited by 2
  8. 2024Incentivized Truthful Communication for Federated Banditscited by 2
  9. 2024Provable Mutual Benefits from Federated Learning in Privacy-Sensitive Domainscited by 2
  10. 2024Inference Attacks: A Taxonomy, Survey, and Promising Directionscited by 2
  11. 2022Long-term Data Sharing under Exclusivity Attackscited by 1
  12. 2023Federated Learning as a Network Effects Gamecited by 1
  13. 2023Dynamic Fair Federated Learning Based on Reinforcement Learningcited by 1
  14. 2023Cross-Silo Federated Learning Across Divergent Domains with Iterative Parameter Alignmentcited by 1
  15. 2025Online Federation For Mixtures of Proprietary Agents with Black-Box Encoderscited by 1
  16. 2025Incentivize Contribution and Learn Parameters Too: Federated Learning with Strategic Data Ownerscited by 1
  17. 2023Incentivized Collaboration in Active Learningcited by 0
  18. 2023Sample Complexity of Linear Regression Models for Opinion Formation in Networkscited by 0
  19. 2024Defection-Free Collaboration between Competitors in a Learning Systemcited by 0
  20. 2025Tackling Heterogeneity in Federated Learning via Variance-Reduced Boltzmann Sampling within Homogeneous Social Coalitionscited by 0
  21. 2025A Cram'er-von Mises Approach to Incentivizing Truthful Data Sharingcited by 0
  22. 2025Incentivizing High-quality Participation From Federated Learning Agentscited by 0
  23. 2026Incentive-Aware Federated Averaging with Performance Guarantees under Strategic Participationcited by 0
  24. 2026Stable and Budget-Feasible Coalition Formation for Clustered Federated Learning: A Hedonic Potential-Game Approachcited by 0
  25. 2026Performative Privacy: When Differential Privacy Maximizes Utilitycited by 0
  26. 2026Pathwise Individual Rationality in Federated Learning: A Mechanism-Architecture Co-Designcited by 0
  27. 2026Federated Agent Optimizationcited by 0