Neural Collapse Inspired Federated Learning with Non-iid Data

TL;DR

This paper introduces a federated learning method inspired by neural collapse, using a fixed global structure and category memory vectors to improve performance and convergence on non-iid data.

Contribution

It proposes a novel approach that leverages neural collapse principles and fixed global structures to enhance federated learning with non-iid data.

Findings

Improved accuracy on heterogeneous datasets

Faster convergence compared to baseline methods

Effective handling of non-iid data distributions

Abstract

One of the challenges in federated learning is the non-independent and identically distributed (non-iid) characteristics between heterogeneous devices, which cause significant differences in local updates and affect the performance of the central server. Although many studies have been proposed to address this challenge, they only focus on local training and aggregation processes to smooth the changes and fail to achieve high performance with deep learning models. Inspired by the phenomenon of neural collapse, we force each client to be optimized toward an optimal global structure for classification. Specifically, we initialize it as a random simplex Equiangular Tight Frame (ETF) and fix it as the unit optimization target of all clients during the local updating. After guaranteeing all clients are learning to converge to the global optimum, we propose to add a global memory vector for each category to remedy the parameter fluctuation caused by the bias of the intra-class condition distribution among clients. Our experimental results show that our method can improve the performance with faster convergence speed on different-size datasets.