On the Effect of Defection in Federated Learning and How to Prevent It

Minbiao Han, Kumar Kshitij Patel, Han Shao, Lingxiao Wang

Primary Area: societal considerations including fairness, safety, privacy

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Incentive Design, Optimization, Robustness, Federated Learning, Fairness, Adaptive Optimization

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We study the effect of devices permanently dropping out of federated optimization and provide a new algorithm to provably avoid defections.

Abstract: Federated learning is a machine learning protocol that enables a large population of agents to collaborate. These agents communicate over multiple rounds to produce a single, consensus model. Despite this collaborative framework, there are instances 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 such defections can have on the final model's robustness and ability to generalize. We also show that current federated optimization algorithms fall short in disincentivizing these harmful defections. To address this, 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.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 8625