Heterogeneous Federated Learning

TL;DR

This paper introduces a novel federated learning framework that aligns model structures and feature information across heterogeneous models, improving convergence speed, accuracy, and efficiency in diverse data distribution scenarios.

Contribution

It proposes a feature-oriented regulation method ({$ ext{Ψ}$-Net}) for explicit feature allocation, enabling early structure matching and improved model alignment in federated learning.

Findings

Enhanced model alignment in heterogeneous federated learning.

Improved convergence speed and accuracy.

Effective in both IID and non-IID data scenarios.

Abstract

Federated learning learns from scattered data by fusing collaborative models from local nodes. However, due to chaotic information distribution, the model fusion may suffer from structural misalignment with regard to unmatched parameters. In this work, we propose a novel federated learning framework to resolve this issue by establishing a firm structure-information alignment across collaborative models. Specifically, we design a feature-oriented regulation method ({$\Psi$-Net}) to ensure explicit feature information allocation in different neural network structures. Applying this regulating method to collaborative models, matchable structures with similar feature information can be initialized at the very early training stage. During the federated learning process under either IID or non-IID scenarios, dedicated collaboration schemes further guarantee ordered information distribution with definite structure matching, so as the comprehensive model alignment. Eventually, this framework effectively enhances the federated learning applicability to extensive heterogeneous settings, while providing excellent convergence speed, accuracy, and computation/communication efficiency.