Subgraph Federated Learning with Missing Neighbor Generation

TL;DR

This paper introduces FedSage and FedSage+ for subgraph federated learning, enabling collaborative graph model training across distributed subgraphs with missing links, demonstrating effectiveness on real datasets.

Contribution

It proposes novel federated learning techniques for subgraphs, including missing neighbor generation, to improve model generalization without sharing raw graph data.

Findings

Effective on four real-world datasets

Improves handling of missing links across subgraphs

Demonstrates theoretical generalization benefits

Abstract

Graphs have been widely used in data mining and machine learning due to their unique representation of real-world objects and their interactions. As graphs are getting bigger and bigger nowadays, it is common to see their subgraphs separately collected and stored in multiple local systems. Therefore, it is natural to consider the subgraph federated learning setting, where each local system holds a small subgraph that may be biased from the distribution of the whole graph. Hence, the subgraph federated learning aims to collaboratively train a powerful and generalizable graph mining model without directly sharing their graph data. In this work, towards the novel yet realistic setting of subgraph federated learning, we propose two major techniques: (1) FedSage, which trains a GraphSage model based on FedAvg to integrate node features, link structures, and task labels on multiple local subgraphs; (2) FedSage+, which trains a missing neighbor generator along FedSage to deal with missing links across local subgraphs. Empirical results on four real-world graph datasets with synthesized subgraph federated learning settings demonstrate the effectiveness and efficiency of our proposed techniques. At the same time, consistent theoretical implications are made towards their generalization ability on the global graphs.