Feature Diversification and Adaptation for Federated Domain Generalization

TL;DR

This paper proposes a federated learning approach that uses feature diversification and adaptive inference to improve domain generalization, achieving state-of-the-art results while preserving privacy.

Contribution

It introduces federated feature diversification using global feature statistics and an instance-adaptive inference method to enhance domain generalization in federated learning.

Findings

Achieves state-of-the-art performance on domain generalization benchmarks.

Effectively learns client-invariant representations while preserving privacy.

Reduces domain gap through dynamic feature statistic adjustment.

Abstract

Federated learning, a distributed learning paradigm, utilizes multiple clients to build a robust global model. In real-world applications, local clients often operate within their limited domains, leading to a `domain shift' across clients. Privacy concerns limit each client's learning to its own domain data, which increase the risk of overfitting. Moreover, the process of aggregating models trained on own limited domain can be potentially lead to a significant degradation in the global model performance. To deal with these challenges, we introduce the concept of federated feature diversification. Each client diversifies the own limited domain data by leveraging global feature statistics, i.e., the aggregated average statistics over all participating clients, shared through the global model's parameters. This data diversification helps local models to learn client-invariant representations while preserving privacy. Our resultant global model shows robust performance on unseen test domain data. To enhance performance further, we develop an instance-adaptive inference approach tailored for test domain data. Our proposed instance feature adapter dynamically adjusts feature statistics to align with the test input, thereby reducing the domain gap between the test and training domains. We show that our method achieves state-of-the-art performance on several domain generalization benchmarks within a federated learning setting.