FedMCSA: Personalized Federated Learning via Model Components Self-Attention

TL;DR

FedMCSA introduces a novel self-attention mechanism for federated learning that focuses on model components, effectively handling Non-IID data and improving collaboration among clients.

Contribution

It proposes a new framework using model components self-attention to enhance personalization and cooperation in federated learning with Non-IID data.

Findings

Outperforms previous methods on four benchmark datasets.

Self-attention mechanism improves model collaboration and personalization.

Significantly enhances federated learning performance with Non-IID data.

Abstract

Federated learning (FL) facilitates multiple clients to jointly train a machine learning model without sharing their private data. However, Non-IID data of clients presents a tough challenge for FL. Existing personalized FL approaches rely heavily on the default treatment of one complete model as a basic unit and ignore the significance of different layers on Non-IID data of clients. In this work, we propose a new framework, federated model components self-attention (FedMCSA), to handle Non-IID data in FL, which employs model components self-attention mechanism to granularly promote cooperation between different clients. This mechanism facilitates collaboration between similar model components while reducing interference between model components with large differences. We conduct extensive experiments to demonstrate that FedMCSA outperforms the previous methods on four benchmark datasets. Furthermore, we empirically show the effectiveness of the model components self-attention mechanism, which is complementary to existing personalized FL and can significantly improve the performance of FL.