Hypergraph-MLP: Learning on Hypergraphs without Message Passing

TL;DR

Hypergraph-MLP introduces a message-passing-free learning framework for hypergraph data, using an MLP supervised by hypergraph signal smoothness, achieving competitive accuracy with improved speed and robustness.

Contribution

It presents a novel hypergraph learning method that eliminates message passing, reducing complexity and increasing robustness while maintaining competitive performance.

Findings

Achieves competitive node classification accuracy.

Significantly faster inference compared to message-passing models.

More robust against structural perturbations.

Abstract

Hypergraphs are vital in modelling data with higher-order relations containing more than two entities, gaining prominence in machine learning and signal processing. Many hypergraph neural networks leverage message passing over hypergraph structures to enhance node representation learning, yielding impressive performances in tasks like hypergraph node classification. However, these message-passing-based models face several challenges, including oversmoothing as well as high latency and sensitivity to structural perturbations at inference time. To tackle those challenges, we propose an alternative approach where we integrate the information about hypergraph structures into training supervision without explicit message passing, thus also removing the reliance on it at inference. Specifically, we introduce Hypergraph-MLP, a novel learning framework for hypergraph-structured data, where the learning model is a straightforward multilayer perceptron (MLP) supervised by a loss function based on a notion of signal smoothness on hypergraphs. Experiments on hypergraph node classification tasks demonstrate that Hypergraph-MLP achieves competitive performance compared to existing baselines, and is considerably faster and more robust against structural perturbations at inference.