Hypergraphs as an expressive and general structure have attracted considerable attention from various research domains. Most existing hypergraph node representation learning techniques are based on graph neural networks, and thus adopt the two-stage message passing paradigm (i.e. node -> hyperedge -> node). This paradigm only focuses on local information propagation and does not effectively take into account global information, resulting in less optimal representations. Our theoretical analysis of representative two-stage message passing methods shows that, mathematically, they model different ways of local message passing through hyperedges, and can be unified into one-stage message passing (i.e. node -> node). However, they still only model local information. Motivated by this theoretical analysis, we propose a novel one-stage message passing paradigm to model both global and local information propagation for hypergraphs. We integrate this paradigm into HGraphormer, a Transformer-based framework for hypergraph node representation learning. HGraphormer injects the hypergraph structure information (local information) into Transformers (global information) by combining the attention matrix and hypergraph Laplacian. Extensive experiments demonstrate that HGraphormer outperforms recent hypergraph learning methods on five representative benchmark datasets on the semi-supervised hypernode classification task, setting new state-of-the-art performance, with accuracy improvements between 2.52% and 6.70%. Our code and datasets are available.

翻译：超图作为一种表达能力丰富且结构通用的建模工具，已引起多个研究领域的广泛关注。现有超图节点表示学习技术主要基于图神经网络，普遍采用两阶段消息传递范式（即节点→超边→节点）。该范式仅关注局部信息传播，未能有效整合全局信息，导致表示结果欠优。通过对代表性两阶段消息传递方法进行理论分析，我们发现：从数学本质看，这些方法通过超边建模了不同形式的局部消息传递过程，且可统一为一阶段消息传递范式（即节点→节点）。然而，它们仍仅能建模局部信息。受此理论分析启发，我们提出了一种新颖的一阶段消息传递范式，用于同时建模超图的全局与局部信息传播。我们将该范式集成到HGraphormer中——一个基于Transformer的超图节点表示学习框架。HGraphormer通过融合注意力矩阵与超图拉普拉斯算子，将超图结构信息（局部信息）注入Transformer（全局信息）。大量实验表明，在半监督超节点分类任务上，HGraphormer在五个代表性基准数据集上均超越现有超图学习方法，以2.52%至6.70%的准确率提升创下新的最优性能。我们的代码与数据集已公开。