Virtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learning

TL;DR

This paper introduces FedVN, a federated graph learning framework that uses shared virtual nodes and personalized edge generation to mitigate distribution shifts across clients, improving GNN training performance.

Contribution

FedVN is the first framework to eliminate distribution shifts in federated graph learning using shared virtual nodes and client-specific augmentation strategies.

Findings

FedVN outperforms nine baselines on four datasets.

Theoretical analysis confirms FedVN's ability to eliminate distribution shifts.

Client-specific graph augmentation improves model robustness.

Abstract

Federated Graph Learning (FGL) enables multiple clients to jointly train powerful graph learning models, e.g., Graph Neural Networks (GNNs), without sharing their local graph data for graph-related downstream tasks, such as graph property prediction. In the real world, however, the graph data can suffer from significant distribution shifts across clients as the clients may collect their graph data for different purposes. In particular, graph properties are usually associated with invariant label-relevant substructures (i.e., subgraphs) across clients, while label-irrelevant substructures can appear in a client-specific manner. The issue of distribution shifts of graph data hinders the efficiency of GNN training and leads to serious performance degradation in FGL. To tackle the aforementioned issue, we propose a novel FGL framework entitled FedVN that eliminates distribution shifts through client-specific graph augmentation strategies with multiple learnable Virtual Nodes (VNs). Specifically, FedVN lets the clients jointly learn a set of shared VNs while training a global GNN model. To eliminate distribution shifts, each client trains a personalized edge generator that determines how the VNs connect local graphs in a client-specific manner. Furthermore, we provide theoretical analyses indicating that FedVN can eliminate distribution shifts of graph data across clients. Comprehensive experiments on four datasets under five settings demonstrate the superiority of our proposed FedVN over nine baselines.