Selective Knowledge Sharing for Personalized Federated Learning Under Capacity Heterogeneity

TL;DR

This paper introduces Pa3dFL, a framework for personalized federated learning that effectively handles capacity heterogeneity by decoupling and selectively sharing knowledge, improving model utility for low-capacity devices.

Contribution

The paper proposes a novel approach to personalize federated models by decomposing layers, maintaining uniform general parameters, and generating size-varying personal parameters with a hyper-network.

Findings

Pa3dFL outperforms baseline methods across datasets.

It maintains competitive communication and computation efficiency.

The framework effectively handles capacity heterogeneity in federated learning.

Abstract

Federated Learning (FL) stands to gain significant advantages from collaboratively training capacity-heterogeneous models, enabling the utilization of private data and computing power from low-capacity devices. However, the focus on personalizing capacity-heterogeneous models based on client-specific data has been limited, resulting in suboptimal local model utility, particularly for low-capacity clients. The heterogeneity in both data and device capacity poses two key challenges for model personalization: 1) accurately retaining necessary knowledge embedded within reduced submodels for each client, and 2) effectively sharing knowledge through aggregating size-varying parameters. To this end, we introduce Pa3dFL, a novel framework designed to enhance local model performance by decoupling and selectively sharing knowledge among capacity-heterogeneous models. First, we decompose each layer of the model into general and personal parameters. Then, we maintain uniform sizes for the general parameters across clients and aggregate them through direct averaging. Subsequently, we employ a hyper-network to generate size-varying personal parameters for clients using learnable embeddings. Finally, we facilitate the implicit aggregation of personal parameters by aggregating client embeddings through a self-attention module. We conducted extensive experiments on three datasets to evaluate the effectiveness of Pa3dFL. Our findings indicate that Pa3dFL consistently outperforms baseline methods across various heterogeneity settings. Moreover, Pa3dFL demonstrates competitive communication and computation efficiency compared to baseline approaches, highlighting its practicality and adaptability in adverse system conditions.