Subgraph Federated Learning via Spectral Methods
This addresses privacy and scalability challenges in federated learning for graph data, though it appears incremental as it builds on existing FL methods with a novel spectral approach.
The paper tackles federated learning with graph-structured data across interconnected subgraphs, proposing FedLap to address privacy and scalability issues by using Laplacian smoothing in the spectral domain, achieving competitive or superior utility in experiments.
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.