Training-Free Message Passing for Learning on Hypergraphs

TL;DR

This paper introduces a training-free message passing module for hypergraph neural networks that reduces training time while maintaining competitive performance, enabling efficient learning on complex data structures.

Contribution

The authors propose TF-MP-Module, a precomputable message passing method that decouples hypergraph structure from training, improving efficiency and robustness in hypergraph neural networks.

Findings

TF-HNN is more training-efficient than existing HNNs.

TF-HNN utilizes as much information as existing HNNs for node features.

TF-HNN is robust against oversmoothing and long-range interactions.

Abstract

Hypergraphs are crucial for modelling higher-order interactions in real-world data. Hypergraph neural networks (HNNs) effectively utilise these structures by message passing to generate informative node features for various downstream tasks like node classification. However, the message passing module in existing HNNs typically requires a computationally intensive training process, which limits their practical use. To tackle this challenge, we propose an alternative approach by decoupling the usage of hypergraph structural information from the model learning stage. This leads to a novel training-free message passing module, named TF-MP-Module, which can be precomputed in the data preprocessing stage, thereby reducing the computational burden. We refer to the hypergraph neural network equipped with our TF-MP-Module as TF-HNN. We theoretically support the efficiency and effectiveness of TF-HNN by showing that: 1) It is more training-efficient compared to existing HNNs; 2) It utilises as much information as existing HNNs for node feature generation; and 3) It is robust against the oversmoothing issue while using long-range interactions. Experiments based on seven real-world hypergraph benchmarks in node classification and hyperlink prediction show that, compared to state-of-the-art HNNs, TF-HNN exhibits both competitive performance and superior training efficiency. Specifically, on the large-scale benchmark, Trivago, TF-HNN outperforms the node classification accuracy of the best baseline by 10% with just 1% of the training time of that baseline.