FedAH: Aggregated Head for Personalized Federated Learning

TL;DR

FedAH is a novel personalized federated learning method that aggregates local and global model heads at each iteration, enhancing personalization and global knowledge sharing, leading to improved accuracy across diverse datasets.

Contribution

Introduces FedAH, a new PFL approach that performs element-level aggregation of model heads to balance personalization and global learning.

Findings

FedAH outperforms 10 state-of-the-art FL methods by 2.87% in accuracy.

FedAH maintains performance even with client dropouts.

Extensive experiments on vision and NLP datasets validate effectiveness.

Abstract

Recently, Federated Learning (FL) has gained popularity for its privacy-preserving and collaborative learning capabilities. Personalized Federated Learning (PFL), building upon FL, aims to address the issue of statistical heterogeneity and achieve personalization. Personalized-head-based PFL is a common and effective PFL method that splits the model into a feature extractor and a head, where the feature extractor is collaboratively trained and shared, while the head is locally trained and not shared. However, retaining the head locally, although achieving personalization, prevents the model from learning global knowledge in the head, thus affecting the performance of the personalized model. To solve this problem, we propose a novel PFL method called Federated Learning with Aggregated Head (FedAH), which initializes the head with an Aggregated Head at each iteration. The key feature of FedAH is to perform element-level aggregation between the local model head and the global model head to introduce global information from the global model head. To evaluate the effectiveness of FedAH, we conduct extensive experiments on five benchmark datasets in the fields of computer vision and natural language processing. FedAH outperforms ten state-of-the-art FL methods in terms of test accuracy by 2.87%. Additionally, FedAH maintains its advantage even in scenarios where some clients drop out unexpectedly. Our code is open-accessed at https://github.com/heyuepeng/FedAH.