FedFN: Feature Normalization for Alleviating Data Heterogeneity Problem in Federated Learning

Seongyoon Kim, Gihun Lee, Jaehoon Oh, Se-Young Yun

Student Author Indication: Yes

Keywords: Federated Learning, Weight Bias, Feature Bias, Feature Normalization

TL;DR: We observe that increasing data heterogeneity leads to larger feature norm disparities between global and local models, which are influenced by feature norm bias within local models. We address this issue by introducing feature normalization.

Abstract:

Federated Learning (FL) is a collaborative method for training models while preserving data privacy in decentralized settings. However, FL encounters challenges related to data heterogeneity, which can result in performance degradation. In our study, we observe that as data heterogeneity increases, feature representation in the FedAVG model deteriorates more significantly compared to classifier weight.
Additionally, we observe that as data heterogeneity increases, the gap between higher feature norms for observed classes, obtained from local models, and feature norms of unobserved classes widens, in contrast to the behavior of classifier weight norms. This widening gap extends to encompass the feature norm disparities between local and the global models. To address these issues, we introduce Federated Averaging with Feature Normalization Update (FedFN), a straightforward learning method. We demonstrate the superior performance of FedFN through extensive experiments, even when applied to pretrained ResNet18. Subsequently, we confirm the applicability of FedFN to foundation models.

Submission Number: 57