Federated Hypergraph Learning with Local Differential Privacy: Toward Privacy-Aware Hypergraph Structure Completion

TL;DR

This paper introduces FedHGL, a novel framework for federated hypergraph learning that preserves high-order structural information and guarantees node privacy using local differential privacy mechanisms.

Contribution

FedHGL is the first framework enabling federated hypergraph learning with a hyperedge completion mechanism and formal privacy guarantees, addressing high-order information loss and privacy concerns.

Findings

Effective hyperedge completion preserves structural integrity.

Achieves superior performance over traditional federated graph learning methods.

Provides formal local differential privacy guarantees.

Abstract

The rapid growth of graph-structured data necessitates partitioning and distributed storage across decentralized systems, driving the emergence of federated graph learning to collaboratively train Graph Neural Networks (GNNs) without compromising privacy. However, current methods exhibit limited performance when handling hypergraphs, which inherently represent complex high-order relationships beyond pairwise connections. Partitioning hypergraph structures across federated subsystems amplifies structural complexity, hindering high-order information mining and compromising local information integrity. To bridge the gap between hypergraph learning and federated systems, we develop FedHGL, a first-of-its-kind framework for federated hypergraph learning on disjoint and privacy-constrained hypergraph partitions. Beyond collaboratively training a comprehensive hypergraph neural network across multiple clients, FedHGL introduces a pre-propagation hyperedge completion mechanism to preserve high-order structural integrity within each client. This procedure leverages the federated central server to perform cross-client hypergraph convolution without exposing internal topological information, effectively mitigating the high-order information loss induced by subgraph partitioning. Furthermore, by incorporating two kinds of local differential privacy (LDP) mechanisms, we provide formal privacy guarantees for this process, ensuring that sensitive node features remain protected against inference attacks from potentially malicious servers or clients. Experimental results on seven real-world datasets confirm the effectiveness of our approach and demonstrate its performance advantages over traditional federated graph learning methods.