English

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

Machine Learning 2019-05-23 v4 Machine Learning

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.

Keywords

Cite

@article{arxiv.1809.02589,
  title  = {HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs},
  author = {Naganand Yadati and Madhav Nimishakavi and Prateek Yadav and Vikram Nitin and Anand Louis and Partha Talukdar},
  journal= {arXiv preprint arXiv:1809.02589},
  year   = {2019}
}
R2 v1 2026-06-23T03:58:18.641Z