Line Hypergraph Convolution Network: Applying Graph Convolution for Hypergraphs

TL;DR

This paper introduces a novel method for applying graph convolution to hypergraphs using line graphs, enabling modeling of high-order relationships in complex network data.

Contribution

It proposes the first use of line graphs for hypergraph convolution, extending GCN applicability to hypergraphs with variable hyperedge sizes.

Findings

Outperforms existing hypergraph learning methods on real datasets

Effectively models high-order relationships in complex networks

Demonstrates scalability and robustness of the approach

Abstract

Network representation learning and node classification in graphs got significant attention due to the invent of different types graph neural networks. Graph convolution network (GCN) is a popular semi-supervised technique which aggregates attributes within the neighborhood of each node. Conventional GCNs can be applied to simple graphs where each edge connects only two nodes. But many modern days applications need to model high order relationships in a graph. Hypergraphs are effective data types to handle such complex relationships. In this paper, we propose a novel technique to apply graph convolution on hypergraphs with variable hyperedge sizes. We use the classical concept of line graph of a hypergraph for the first time in the hypergraph learning literature. Then we propose to use graph convolution on the line graph of a hypergraph. Experimental analysis on multiple real world network datasets shows the merit of our approach compared to state-of-the-arts.