Message Passing Neural Networks for Hypergraphs

TL;DR

This paper introduces a message passing neural network designed specifically for hypergraphs, demonstrating its effectiveness over existing models in node classification tasks and emphasizing the advantages of hypergraph representations.

Contribution

It presents a new neural network model that generalizes existing hypergraph models and defines a design space for hypergraph neural networks.

Findings

Outperforms state-of-the-art graph and hypergraph models on node classification

Highlights benefits of hypergraph representations over graph equivalents

Discusses limitations of using graphs for multi-object relations

Abstract

Hypergraph representations are both more efficient and better suited to describe data characterized by relations between two or more objects. In this work, we present a new graph neural network based on message passing capable of processing hypergraph-structured data. We show that the proposed model defines a design space for neural network models for hypergraphs, thus generalizing existing models for hypergraphs. We report experiments on a benchmark dataset for node classification, highlighting the effectiveness of the proposed model with respect to other state-of-the-art methods for graphs and hypergraphs. We also discuss the benefits of using hypergraph representations and, at the same time, highlight the limitation of using equivalent graph representations when the underlying problem has relations among more than two objects.