A General Aggregation Federated Learning Intervention Algorithm based on $do$-Calculus
Keywords: Federated Learning, do-Calculus, causal
TL;DR: A General Aggregation FL Intervention Algorithm based on $do$-Calculus
Abstract: This article explores federated long-tail learning (Fed-LT) tasks, which involve clients with private and heterogeneous data that exhibit a long-tail distribution. We propose two methods: (a) Client Re-weighted Prior Analyzer (CRePA), which balances the global model's performance on tail and non-tail categories and enhances performance on tail categories while maintaining it on non-tail categories. (b) Federated Long-Tail Causal Intervention Model (FedLT-CI) computes clients' causal effects on the global model's performance in the tail and enhances the interpretability of Fed-LT. CRePA achieves state-of-the-art performance, and FedLT-CI improves tail performance significantly without affecting non-tail performance. Extensive experiments indicate that CRePA achieved SOTA performance compared to other baselines on CIFAR-10-LT and CIFAR-100-LT. Applying the FedLT-CI to all baselines significantly improved tail performance without affecting non-tail performance.
Primary Area: causal reasoning
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.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
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: 4369
Loading