mlsanityData to 14 Oct 2026

On the Effect of Defections in Federated Learning and How to Prevent Them

arXiv 2311.16459 ↗First posted 28 Nov 2023cs.LG cs.DC cs.GTcited by 5

Not on the map. Why?

Abstract (arXiv)

Federated learning is a machine learning protocol that enables a large population of agents to collaborate over multiple rounds to produce a single consensus model. There are several federated learning applications where agents may choose to defect permanently-essentially withdrawing from the collaboration-if they are content with their instantaneous model in that round. This work demonstrates the detrimental impact of such defections on the final model's robustness and ability to generalize. We also show that current federated optimization algorithms fail to disincentivize these harmful defections. We introduce a novel optimization algorithm with theoretical guarantees to prevent defections while ensuring asymptotic convergence to an effective solution for all participating agents. We also provide numerical experiments to corroborate our findings and demonstrate the effectiveness of our algorithm.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 21 of its 43 references that are in the map. First posted on arXiv 28 Nov 2023.

Builds on

21 of 43 references.

References · 21

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 629
  4. 2019Privacy-preserving Federated Brain Tumour Segmentationcited by 169
  5. 2020Minibatch vs Local SGD for Heterogeneous Distributed Learningcited by 147
  6. 2021FairFed: Enabling Group Fairness in Federated Learningcited by 118
  7. 2021Federated Evaluation and Tuning for On-Device Personalization: System Design & Applicationscited by 85
  8. 2020Collaborative Machine Learning with Incentive-Aware Model Rewardscited by 71
  9. 2020Federated Learning for Breast Density Classification: A Real-World Implementationcited by 62
  10. 2021Federated Linear Contextual Banditscited by 61
  11. 2021Deep Federated Learning for Autonomous Drivingcited by 54
  12. 2020FMore: An Incentive Scheme of Multi-dimensional Auction for Federated Learning in MECcited by 48
9 more
  1. 2020A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learningcited by 41
  2. 2021One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learningcited by 39
  3. 2022Mechanisms that Incentivize Data Sharing in Federated Learningcited by 39
  4. 2020Trading Data For Learning: Incentive Mechanism For On-Device Federated Learningcited by 21
  5. 2021Enabling Long-Term Cooperation in Cross-Silo Federated Learning: A Repeated Game Perspectivecited by 14
  6. 2021A Contract Theory based Incentive Mechanism for Federated Learningcited by 13
  7. 2020Incentives for Federated Learning: a Hypothesis Elicitation Approachcited by 12
  8. 2020A VCG-based Fair Incentive Mechanism for Federated Learningcited by 11
  9. 2021FL-Market: Trading Private Models in Federated Learningcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 1; 2026: 1.

5 papers.

  1. 2024The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communicationcited by 12
  2. 2024Incentivizing Truthful Collaboration in Heterogeneous Federated Learningcited by 3
  3. 2024Defection-Free Collaboration between Competitors in a Learning Systemcited by 0
  4. 2025Personalized Federated Training of Diffusion Models with Privacy Guaranteescited by 0
  5. 2026What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneitycited by 0