Achieving Exact Federated Unlearning with Improved Post-Unlearning Performance

Ze Yu Zhang, Bui Thi Cam Nhung, Arun Verma, Bolin Ding, Bryan Kian Hsiang Low

Keywords: Exact Federated Unlearning, Improved Post-Unlearning Performance, Multi-Models Training

TL;DR: This paper proposes methods for federated learning that ensure exact federated unlearning while achieving a better performance post-unlearning than retraining from scratch.

Abstract: Federated learning is a machine learning paradigm that allows multiple clients to train aggregated model via sharing model updates to a central server without sharing their data. Even though the data is not shared, it can indirectly influence the aggregated model via the shared model updates. In many real-life scenarios, we need to completely remove a client's influence (unlearning) from the aggregated model, such as competitive clients who want to remove their influence from the aggregated model after leaving the coalition to ensure other clients do not benefit from their contributions. The influence removal is also needed when the adversarial client negatively affects the aggregated model. Though the aggregated model can be retrained from scratch to ensure exact unlearning (completely removing the client's influence from the aggregated model), it performs poorly just after the unlearning, which is undesirable during deployment. To overcome this challenge, this paper proposes federated unlearning algorithms that ensure exact unlearning while achieving better performance post-unlearning. Our experimental results on different real datasets validate the performance of the proposed algorithms.

Primary Area: other topics in machine learning (i.e., none of the above)

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.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

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: 14278