mlsanityData to 7 Oct 2026

Incentivizing Truthful Collaboration in Heterogeneous Federated Learning

arXiv 2412.00980 ↗First posted 1 Dec 2024cs.LG cs.GT stat.MLcited by 3

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is a distributed collaborative learning method, where multiple clients learn together by sharing gradient updates instead of raw data. However, it is well-known that FL is vulnerable to manipulated updates from clients. In this work we study the impact of data heterogeneity on clients' incentives to manipulate their updates. First, we present heterogeneous collaborative learning scenarios where a client can modify their updates to be better off, and show that these manipulations can lead to diminishing model performance. To prevent such modifications, we formulate a game in which clients may misreport their gradient updates in order to "steer" the server model to their advantage. We develop a payment rule that provably disincentivizes sending modified updates under the FedSGD protocol. We derive explicit bounds on the clients' payments and the convergence rate of the global model, which allows us to study the trade-off between heterogeneity, payments and convergence. Finally, we provide an experimental evaluation of the effectiveness of our payment rule in the FedSGD, median-based aggregation FedSGD and FedAvg protocols on three tasks in computer vision and natural language processing. In all cases we find that our scheme successfully disincentivizes modifications.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 30 of its 39 references that are in the map. First posted on arXiv 1 Dec 2024.

Builds on

30 of 39 references.

References · 30

  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. 2016Optimization Methods for Large-Scale Machine Learningcited by 1,140
  4. 2018LEAF: A Benchmark for Federated Settingscited by 780
  5. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  6. 2020The Future of Digital Health with Federated Learningcited by 625
  7. 2020A Unified Theory of Decentralized SGD with Changing Topology and Local Updatescited by 361
  8. 2020Three Approaches for Personalization with Applications to Federated Learningcited by 321
  9. 2019Robust Aggregation for Federated Learningcited by 314
  10. 2019Tighter Theory for Local SGD on Identical and Heterogeneous Datacited by 266
  11. 2020Minibatch vs Local SGD for Heterogeneous Distributed Learningcited by 147
  12. 2021Federated Learning for Open Bankingcited by 138
18 more
  1. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 116
  2. 2018Byzantine Stochastic Gradient Descentcited by 81
  3. 2020Model-sharing Games: Analyzing Federated Learning Under Voluntary Participationcited by 60
  4. 2021Personalized Federated Learning through Local Memorizationcited by 57
  5. 2020Mitigating Bias in Federated Learningcited by 56
  6. 2021Incentive Mechanisms for Federated Learning: From Economic and Game Theoretic Perspectivecited by 47
  7. 2021Optimality and Stability in Federated Learning: A Game-theoretic Approachcited by 40
  8. 2021One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learningcited by 39
  9. 2021Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspectivecited by 38
  10. 2022Mechanisms that Incentivize Data Sharing in Federated Learningcited by 38
  11. 2021The Role of Cross-Silo Federated Learning in Facilitating Data Sharing in the Agri-Food Sectorcited by 16
  12. 2024The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communicationcited by 12
  13. 2021Linear Speedup in Personalized Collaborative Learningcited by 8
  14. 2023Partially Personalized Federated Learning: Breaking the Curse of Data Heterogeneitycited by 8
  15. 2023Evaluating and Incentivizing Diverse Data Contributions in Collaborative Learningcited by 8
  16. 2023Incentivizing Honesty among Competitors in Collaborative Learning and Optimizationcited by 6
  17. 2023On the Effect of Defections in Federated Learning and How to Prevent Themcited by 4
  18. 2024Provable Mutual Benefits from Federated Learning in Privacy-Sensitive Domainscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Incentivize Contribution and Learn Parameters Too: Federated Learning with Strategic Data Ownerscited by 1
  2. 2026Incentive-Aware Federated Averaging with Performance Guarantees under Strategic Participationcited by 0
  3. 2026Gradient Manipulation in Distributed Stochastic Gradient Descent with Strategic Agents: Truthful Incentives with Convergence Guaranteescited by 0