Subgraph Federated Learning via Spectral Methods

TL;DR

This paper introduces FedLap, a spectral method-based federated learning framework for graph-structured data that ensures privacy, scalability, and effective modeling of inter-node dependencies.

Contribution

FedLap is the first subgraph federated learning scheme utilizing spectral methods with strong privacy guarantees and improved scalability.

Findings

FedLap achieves competitive or superior utility on benchmark datasets.

It preserves privacy while capturing inter-node dependencies effectively.

FedLap outperforms existing methods in scalability and privacy protection.

Abstract

We consider the problem of federated learning (FL) with graph-structured data distributed across multiple clients. In particular, we address the prevalent scenario of interconnected subgraphs, where interconnections between clients significantly influence the learning process. Existing approaches suffer from critical limitations, either requiring the exchange of sensitive node embeddings, thereby posing privacy risks, or relying on computationally-intensive steps, which hinders scalability. To tackle these challenges, we propose FedLap, a novel framework that leverages global structure information via Laplacian smoothing in the spectral domain to effectively capture inter-node dependencies while ensuring privacy and scalability. We provide a formal analysis of the privacy of FedLap, demonstrating that it preserves privacy. Notably, FedLap is the first subgraph FL scheme with strong privacy guarantees. Extensive experiments on benchmark datasets demonstrate that FedLap achieves competitive or superior utility compared to existing techniques.