Hypergraphs are crucial for modeling 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 block 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 the hypergraph structural information from the model training stage. The proposed model, simplified hypergraph neural network (SHNN), contains a training-free message-passing block that can be precomputed before the training of SHNN, thereby reducing the computational burden. We theoretically support the efficiency and effectiveness of SHNN 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 six real-world hypergraph benchmarks in node classification and hyperlink prediction present that, compared to state-of-the-art HNNs, SHNN shows both competitive performance and superior training efficiency. Specifically, on Cora-CA, SHNN achieves the highest node classification accuracy with just 2% training time of the best baseline.

翻译：超图对于建模现实世界数据中的高阶交互至关重要。超图神经网络（HNNs）通过消息传递有效利用这些结构，为节点分类等下游任务生成信息丰富的节点特征。然而，现有HNNs中的消息传递模块通常需要计算密集型的训练过程，这限制了其实际应用。为应对这一挑战，我们提出一种替代方法，将超图结构信息的使用与模型训练阶段解耦。所提出的模型——简化超图神经网络（SHNN），包含一个免训练的消息传递模块，该模块可在SHNN训练前预先计算，从而减轻计算负担。我们从理论上支持SHNN的效率和有效性，证明：1）与现有HNNs相比，其训练效率更高；2）在节点特征生成方面，其利用的信息量与现有HNNs相当；3）在使用长程交互的同时，其对过度平滑问题具有鲁棒性。基于六个真实世界超图基准在节点分类和超链接预测上的实验表明，与最先进的HNNs相比，SHNN展现出具有竞争力的性能和更优越的训练效率。具体而言，在Cora-CA数据集上，SHNN仅需最佳基线模型2%的训练时间即实现了最高的节点分类准确率。