Federated Learning With Individualized Privacy Through Client Sampling

TL;DR

This paper introduces a federated learning approach that personalizes privacy levels for each user by adapting client sampling based on individual privacy preferences, improving the privacy-utility trade-off over uniform methods.

Contribution

It extends the SAMPLE algorithm to federated learning, enabling client-specific privacy settings and demonstrating improved performance over existing uniform privacy approaches.

Findings

Outperforms uniform DP baselines in privacy-utility trade-off

Better than SCALE method in client privacy customization

Effective under realistic privacy distributions and multiple datasets

Abstract

With growing concerns about user data collection, individualized privacy has emerged as a promising solution to balance protection and utility by accounting for diverse user privacy preferences. Instead of enforcing a uniform level of anonymization for all users, this approach allows individuals to choose privacy settings that align with their comfort levels. Building on this idea, we propose an adapted method for enabling Individualized Differential Privacy (IDP) in Federated Learning (FL) by handling clients according to their personal privacy preferences. By extending the SAMPLE algorithm from centralized settings to FL, we calculate client-specific sampling rates based on their heterogeneous privacy budgets and integrate them into a modified IDP-FedAvg algorithm. We test this method under realistic privacy distributions and multiple datasets. The experimental results demonstrate that our approach achieves clear improvements over uniform DP baselines, reducing the trade-off between privacy and utility. Compared to the alternative SCALE method in related work, which assigns differing noise scales to clients, our method performs notably better. However, challenges remain for complex tasks with non-i.i.d. data, primarily stemming from the constraints of the decentralized setting.