Communication-Efficient Personalized Federal Graph Learning via Low-Rank Decomposition

TL;DR

This paper introduces CEFGL, a communication-efficient personalized federated graph learning algorithm that decomposes models into low-rank global and sparse local components, significantly reducing communication costs while maintaining high accuracy across diverse datasets.

Contribution

The paper proposes a novel low-rank and sparse decomposition approach for personalized federated graph learning, enhancing communication efficiency and model personalization.

Findings

Achieves optimal classification accuracy across heterogeneous datasets.

Reduces communication bits by a factor of 18.58 compared to state-of-the-art.

Improves accuracy by 5.64% over FedStar in cross-dataset settings.

Abstract

Federated graph learning (FGL) has gained significant attention for enabling heterogeneous clients to process their private graph data locally while interacting with a centralized server, thus maintaining privacy. However, graph data on clients are typically non-IID, posing a challenge for a single model to perform well across all clients. Another major bottleneck of FGL is the high cost of communication. To address these challenges, we propose a communication-efficient personalized federated graph learning algorithm, CEFGL. Our method decomposes the model parameters into low-rank generic and sparse private models. We employ a dual-channel encoder to learn sparse local knowledge in a personalized manner and low-rank global knowledge in a shared manner. Additionally, we perform multiple local stochastic gradient descent iterations between communication phases and integrate efficient compression techniques into the algorithm. The advantage of CEFGL lies in its ability to capture common and individual knowledge more precisely. By utilizing low-rank and sparse parameters along with compression techniques, CEFGL significantly reduces communication complexity. Extensive experiments demonstrate that our method achieves optimal classification accuracy in a variety of heterogeneous environments across sixteen datasets. Specifically, compared to the state-of-the-art method FedStar, the proposed method (with GIN as the base model) improves accuracy by 5.64\% on cross-datasets setting CHEM, reduces communication bits by a factor of 18.58, and reduces the communication time by a factor of 1.65.