Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decomposition

TL;DR

FedDecomp introduces a parameter additive decomposition approach in personalized federated learning, effectively decoupling shared and client-specific knowledge, and employs a low-rank constraint to enhance model capacity and performance.

Contribution

The paper proposes FedDecomp, a novel PFL method that decomposes each model parameter into shared and personalized parts, improving knowledge separation and model efficiency.

Findings

Outperforms state-of-the-art methods by up to 4.9% across datasets.

Effective decoupling of shared and personalized knowledge.

Low-rank constraint enhances model capacity and performance.

Abstract

To address data heterogeneity, the key strategy of Personalized Federated Learning (PFL) is to decouple general knowledge (shared among clients) and client-specific knowledge, as the latter can have a negative impact on collaboration if not removed. Existing PFL methods primarily adopt a parameter partitioning approach, where the parameters of a model are designated as one of two types: parameters shared with other clients to extract general knowledge and parameters retained locally to learn client-specific knowledge. However, as these two types of parameters are put together like a jigsaw puzzle into a single model during the training process, each parameter may simultaneously absorb both general and client-specific knowledge, thus struggling to separate the two types of knowledge effectively. In this paper, we introduce FedDecomp, a simple but effective PFL paradigm that employs parameter additive decomposition to address this issue. Instead of assigning each parameter of a model as either a shared or personalized one, FedDecomp decomposes each parameter into the sum of two parameters: a shared one and a personalized one, thus achieving a more thorough decoupling of shared and personalized knowledge compared to the parameter partitioning method. In addition, as we find that retaining local knowledge of specific clients requires much lower model capacity compared with general knowledge across all clients, we let the matrix containing personalized parameters be low rank during the training process. Moreover, a new alternating training strategy is proposed to further improve the performance. Experimental results across multiple datasets and varying degrees of data heterogeneity demonstrate that FedDecomp outperforms state-of-the-art methods up to 4.9\%. The code is available at https://github.com/XinghaoWu/FedDecomp.