Fed2: Feature-Aligned Federated Learning

TL;DR

Fed2 introduces a feature-aligned federated learning framework that improves model convergence and accuracy by explicitly aligning features across local models, addressing limitations of traditional averaging methods.

Contribution

The paper proposes Fed2, a novel framework with structure adaptation and feature paired averaging to enhance feature alignment in federated learning.

Findings

Improved convergence speed and accuracy in federated learning.

Effective under both IID and non-IID data distributions.

Enhanced computational and communication efficiency.

Abstract

Federated learning learns from scattered data by fusing collaborative models from local nodes. However, the conventional coordinate-based model averaging by FedAvg ignored the random information encoded per parameter and may suffer from structural feature misalignment. In this work, we propose Fed2, a feature-aligned federated learning framework to resolve this issue by establishing a firm structure-feature alignment across the collaborative models. Fed2 is composed of two major designs: First, we design a feature-oriented model structure adaptation method to ensure explicit feature allocation in different neural network structures. Applying the structure adaptation to collaborative models, matchable structures with similar feature information can be initialized at the very early training stage. During the federated learning process, we then propose a feature paired averaging scheme to guarantee aligned feature distribution and maintain no feature fusion conflicts under either IID or non-IID scenarios. Eventually, Fed2 could effectively enhance the federated learning convergence performance under extensive homo- and heterogeneous settings, providing excellent convergence speed, accuracy, and computation/communication efficiency.