A Provably Robust Algorithm for Differentially Private Clustered Federated Learning

27 Sept 2024 (modified: 05 Feb 2025)Submitted to ICLR 2025EveryoneRevisionsBibTeXCC BY 4.0
Keywords: Federated Learning, Clustered Federated Learning, Differential Privacy, Clustering
TL;DR: In order to address performance fairness, we propose a robust differentially private clustered federated learning algorithm, which is augmented with some non-obvious techniques to make it robust to DP noise.
Abstract:

Federated Learning (FL), which is a decentralized machine learning (ML) approach, often incorporates differential privacy (DP) to enhance data privacy guarantees. However, differentially private federated learning (DPFL) introduces performance disparities across clients, particularly affecting minority groups. Some recent works have attempted to address large data heterogeneity in vanilla FL settings through clustering clients, but these methods remain sensitive and prone to errors further exacerbated by the DP noise, making them inappropriate for DPFL settings. We propose an algorithm for differentially private clustered FL, which is robust to the DP noise in the system and identifies clients’ clusters correctly. To this end, we propose to cluster clients based on both their model updates and training loss values. Furthermore, when clustering clients’ model updates, our proposed approach addresses the server’s uncertainties by employing large batch sizes as well as Gaussian Mixture Models (GMM) to reduce the impact of DP and stochastic noise and avoid potential clustering errors. This idea is efficient especially in privacy-sensitive scenarios with more DP noise. We provide theoretical analysis justifying our approach, and evaluate it extensively across diverse data distributions and privacy budgets. Our experimental results show its effectiveness in addressing large data heterogeneity in DPFL systems with a small computational cost.

Supplementary Material: pdf
Primary Area: alignment, fairness, safety, privacy, and societal considerations
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: 10948
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview