HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs

TL;DR

HyperGCN is a novel graph convolutional network designed for semi-supervised learning and combinatorial optimization on hypergraphs, effectively handling complex relationships in real-world network data.

Contribution

This paper introduces HyperGCN, a new GCN model specifically tailored for hypergraph data, extending GCN applications beyond traditional graphs.

Findings

HyperGCN outperforms existing methods on real-world hypergraph datasets.

HyperGCN effectively addresses complex relationships in hypergraphs.

The model is applicable to combinatorial optimization problems on hypergraphs.

Abstract

In many real-world network datasets such as co-authorship, co-citation, email communication, etc., relationships are complex and go beyond pairwise. Hypergraphs provide a flexible and natural modeling tool to model such complex relationships. The obvious existence of such complex relationships in many real-world networks naturaly motivates the problem of learning with hypergraphs. A popular learning paradigm is hypergraph-based semi-supervised learning (SSL) where the goal is to assign labels to initially unlabeled vertices in a hypergraph. Motivated by the fact that a graph convolutional network (GCN) has been effective for graph-based SSL, we propose HyperGCN, a novel GCN for SSL on attributed hypergraphs. Additionally, we show how HyperGCN can be used as a learning-based approach for combinatorial optimisation on NP-hard hypergraph problems. We demonstrate HyperGCN's effectiveness through detailed experimentation on real-world hypergraphs.