FedEBA+: Towards Fair and Effective Federated Learning via Entropy-based Model

Lin Wang, Zhichao Wang, Xiaoying Tang

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: federated learning, fairness algorithm

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

TL;DR: We introduce FedEBA+, a fairness algorithm for federated learning that enhances both client fairness and global model accuracy. We offer theoretical analysis and experimental validation.

Abstract:

Ensuring fairness is a crucial aspect of Federated Learning (FL), which enables the model to perform consistently across all clients.
However, designing an FL algorithm that simultaneously improves global model performance and promotes fairness remains a formidable challenge, as achieving the latter often necessitates a trade-off with the former.
To address this challenge, we propose a new FL algorithm, FedEBA+, which enhances fairness while simultaneously improving global model performance.
FedEBA+ incorporates a fair aggregation scheme that assigns higher weights to underperforming clients and an alignment update method.
In addition, we provide theoretical convergence analysis and show the fairness of FedEBA+.
Extensive experiments demonstrate that FedEBA+ outperforms other SOTA fairness FL methods in terms of both fairness and global model performance.

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: 5023