HyperGCN: A New Method of Training Graph Convolutional Networks 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.
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}
}