Personalized Federated Learning with Adaptive Feature Aggregation and Knowledge Transfer

TL;DR

This paper introduces FedAFK, a novel personalized federated learning method that adaptively aggregates features and transfers knowledge to improve model performance on non-IID data.

Contribution

The paper proposes FedAFK, a new personalized FL approach that enhances feature extraction and balances generalization and personalization for non-IID data.

Findings

FedAFK outperforms 13 state-of-the-art baselines.

Extensive experiments on three datasets demonstrate superior performance.

The method effectively balances personalization and global knowledge transfer.

Abstract

Federated Learning(FL) is popular as a privacy-preserving machine learning paradigm for generating a single model on decentralized data. However, statistical heterogeneity poses a significant challenge for FL. As a subfield of FL, personalized FL (pFL) has attracted attention for its ability to achieve personalized models that perform well on non-independent and identically distributed (Non-IID) data. However, existing pFL methods are limited in terms of leveraging the global model's knowledge to enhance generalization while achieving personalization on local data. To address this, we proposed a new method personalized Federated learning with Adaptive Feature Aggregation and Knowledge Transfer (FedAFK), to train better feature extractors while balancing generalization and personalization for participating clients, which improves the performance of personalized models on Non-IID data. We conduct extensive experiments on three datasets in two widely-used heterogeneous settings and show the superior performance of our proposed method over thirteen state-of-the-art baselines.