A General Aggregation Federated Learning Intervention Algorithm based on $do$-Calculus

Zhenyuan Huang, Haijun Yang, hui Zhang, Chutong Yang

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.

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