Bridging Local and Federated Data Normalization in Federated Learning: A Privacy-Preserving Approach

TL;DR

This paper introduces federated normalization, a privacy-preserving method that enables collaborative data normalization in federated learning, matching pooled normalization performance while safeguarding data privacy.

Contribution

It systematically evaluates normalization techniques in federated learning and proposes novel homomorphic encryption methods for secure, privacy-preserving normalization.

Findings

Federated normalization achieves performance comparable to pooled normalization.

Homomorphic encryption enables secure calculation of normalization parameters.

Privacy-preserving techniques mitigate risks of sharing normalization data.

Abstract

Data normalization is a crucial preprocessing step for enhancing model performance and training stability. In federated learning (FL), where data remains distributed across multiple parties during collaborative model training, normalization presents unique challenges due to the decentralized and often heterogeneous nature of the data. Traditional methods rely on either independent client-side processing, i.e., local normalization, or normalizing the entire dataset before distributing it to parties, i.e., pooled normalization. Local normalization can be problematic when data distributions across parties are non-IID, while the pooled normalization approach conflicts with the decentralized nature of FL. In this paper, we explore the adaptation of widely used normalization techniques to FL and define the term federated normalization. Federated normalization simulates pooled normalization by enabling the collaborative exchange of normalization parameters among parties. Thus, it achieves performance on par with pooled normalization without compromising data locality. However, sharing normalization parameters such as the mean introduces potential privacy risks, which we further mitigate through a robust privacy-preserving solution. Our contributions include: (i) We systematically evaluate the impact of various federated and local normalization techniques in heterogeneous FL scenarios, (ii) We propose a novel homomorphically encrypted $k$-th ranked element (and median) calculation tailored for the federated setting, enabling secure and efficient federated normalization, (iii) We propose privacy-preserving implementations of widely used normalization techniques for FL, leveraging multiparty fully homomorphic encryption (MHE).