HiFGL: A Hierarchical Framework for Cross-silo Cross-device Federated Graph Learning

TL;DR

HiFGL introduces a hierarchical federated graph learning framework that effectively captures complex graph knowledge across heterogeneous clients while ensuring multi-level privacy, demonstrated through theoretical guarantees and extensive real-world experiments.

Contribution

The paper presents a novel hierarchical architecture and a secure message passing scheme for cross-silo cross-device federated graph learning, addressing privacy and graph integrity challenges.

Findings

Achieves multi-level privacy preservation with theoretical guarantees.

Outperforms several baselines on real-world datasets.

Applicable to both cross-silo and cross-device scenarios.

Abstract

Federated Graph Learning (FGL) has emerged as a promising way to learn high-quality representations from distributed graph data with privacy preservation. Despite considerable efforts have been made for FGL under either cross-device or cross-silo paradigm, how to effectively capture graph knowledge in a more complicated cross-silo cross-device environment remains an under-explored problem. However, this task is challenging because of the inherent hierarchy and heterogeneity of decentralized clients, diversified privacy constraints in different clients, and the cross-client graph integrity requirement. To this end, in this paper, we propose a Hierarchical Federated Graph Learning (HiFGL) framework for cross-silo cross-device FGL. Specifically, we devise a unified hierarchical architecture to safeguard federated GNN training on heterogeneous clients while ensuring graph integrity. Moreover, we propose a Secret Message Passing (SecMP) scheme to shield unauthorized access to subgraph-level and node-level sensitive information simultaneously. Theoretical analysis proves that HiFGL achieves multi-level privacy preservation with complexity guarantees. Extensive experiments on real-world datasets validate the superiority of the proposed framework against several baselines. Furthermore, HiFGL's versatile nature allows for its application in either solely cross-silo or cross-device settings, further broadening its utility in real-world FGL applications.