Hypergraph-MLP: Learning on Hypergraphs without Message Passing
This work addresses efficiency and robustness issues in hypergraph learning for researchers and practitioners in machine learning and signal processing, though it is incremental as it builds on existing hypergraph methods.
The paper tackled the challenges of oversmoothing, high latency, and sensitivity to structural perturbations in hypergraph neural networks by proposing Hypergraph-MLP, a framework that integrates hypergraph structure into training supervision without message passing, achieving competitive performance, faster inference, and improved robustness in hypergraph node classification tasks.
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.