Subgraph Federated Learning via Spectral Methods

Javad Aliakbari (Chalmers University of Technology) · Johan Oestman (Recorded Future) · Ashkan Panahi (Chalmers University of Technology) · Alexandre Graell i Amat (Chalmers University of Technology)

benchmark datasetscomputationally-intensivefederated learningfedlapformal analysisgraph-structured datainter-node dependenciesinterconnected subgraphslaplacian smoothingnode embeddings privacy guarantees privacy risks scalability spectral domainsubgraph fl scheme

We consider the problem of federated learning (FL) with graph-structured data distributed across multiple clients. In particular, we address the common 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 the proposed method achieves competitive or superior utility compared to existing techniques.