Research

Paper

TESTING February 26, 2026

Tackling Privacy Heterogeneity in Differentially Private Federated Learning

Authors

Ruichen Xu, Ying-Jun Angela Zhang, Jianwei Huang

Abstract

Differentially private federated learning (DP-FL) enables clients to collaboratively train machine learning models while preserving the privacy of their local data. However, most existing DP-FL approaches assume that all clients share a uniform privacy budget, an assumption that does not hold in real-world scenarios where privacy requirements vary widely. This privacy heterogeneity poses a significant challenge: conventional client selection strategies, which typically rely on data quantity, cannot distinguish between clients providing high-quality updates and those introducing substantial noise due to strict privacy constraints. To address this gap, we present the first systematic study of privacy-aware client selection in DP-FL. We establish a theoretical foundation by deriving a convergence analysis that quantifies the impact of privacy heterogeneity on training error. Building on this analysis, we propose a privacy-aware client selection strategy, formulated as a convex optimization problem, that adaptively adjusts selection probabilities to minimize training error. Extensive experiments on benchmark datasets demonstrate that our approach achieves up to a 10% improvement in test accuracy on CIFAR-10 compared to existing baselines under heterogeneous privacy budgets. These results highlight the importance of incorporating privacy heterogeneity into client selection for practical and effective federated learning.

Metadata

arXiv ID: 2602.22633
Provider: ARXIV
Primary Category: cs.LG
Published: 2026-02-26
Fetched: 2026-02-27 04:35

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.22633v1</id>\n    <title>Tackling Privacy Heterogeneity in Differentially Private Federated Learning</title>\n    <updated>2026-02-26T05:20:37Z</updated>\n    <link href='https://arxiv.org/abs/2602.22633v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.22633v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Differentially private federated learning (DP-FL) enables clients to collaboratively train machine learning models while preserving the privacy of their local data. However, most existing DP-FL approaches assume that all clients share a uniform privacy budget, an assumption that does not hold in real-world scenarios where privacy requirements vary widely. This privacy heterogeneity poses a significant challenge: conventional client selection strategies, which typically rely on data quantity, cannot distinguish between clients providing high-quality updates and those introducing substantial noise due to strict privacy constraints. To address this gap, we present the first systematic study of privacy-aware client selection in DP-FL. We establish a theoretical foundation by deriving a convergence analysis that quantifies the impact of privacy heterogeneity on training error. Building on this analysis, we propose a privacy-aware client selection strategy, formulated as a convex optimization problem, that adaptively adjusts selection probabilities to minimize training error. Extensive experiments on benchmark datasets demonstrate that our approach achieves up to a 10% improvement in test accuracy on CIFAR-10 compared to existing baselines under heterogeneous privacy budgets. These results highlight the importance of incorporating privacy heterogeneity into client selection for practical and effective federated learning.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.DC'/>\n    <published>2026-02-26T05:20:37Z</published>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Ruichen Xu</name>\n    </author>\n    <author>\n      <name>Ying-Jun Angela Zhang</name>\n    </author>\n    <author>\n      <name>Jianwei Huang</name>\n    </author>\n  </entry>"
}