发表机构
University of North Carolina at Chapel Hill; Illinois Institute of Technology（北卡罗来纳大学教堂山分校; 伊利诺伊理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对超图学习缺乏可解释性的问题，提出超图神经加性网络（HGNAN），将神经加性模型扩展至高阶关系数据，在保持与最先进方法相当性能的同时，实现节点级与超边级任务的透明预测。
AI 中文摘要
超图为建模网络化数据提供了一种自然框架，其中实体间的依赖关系由高阶交互所支配。尽管超图学习方法（如超图神经网络）已展现出卓越的预测性能，但现有的大多数方法依赖黑箱消息传递架构，难以厘清节点属性与高阶结构信息各自的贡献。为应对这一挑战，我们提出了超图神经加性网络（HGNAN），一种用于超图结构数据学习的内在可解释框架。HGNAN通过将特征级非线性分解与超图感知的结构聚合相结合，将经典神经加性模型扩展至高阶关系数据，从而在节点级和超边级任务上实现透明预测。在基准数据集上的大量实验表明，HGNAN在取得与最先进超图学习方法相当性能的同时，提供了内在且有意义的可解释性。
英文摘要
Hypergraphs offer a natural framework for modeling networked data, where dependencies among entities are governed by higher-order interactions. While hypergraph learning methods such as hypergraph neural networks have demonstrated remarkable predictive performance, most existing approaches rely on black-box message-passing architectures, making it difficult to disentangle the contributions of node attributes and higher-order structural information. To address this challenge, we introduce the hypergraph neural additive network (HGNAN), an inherently interpretable framework for learning on hypergraph-structured data. HGNAN extends classical neural additive models to higher-order relational data by integrating feature-wise nonlinear decomposition with hypergraph-aware structural aggregation, enabling transparent prediction for both node- and hyperedge-level tasks. Extensive experiments on benchmark datasets demonstrate that HGNAN achieves performance comparable with state-of-the-art hypergraph learning methods while providing intrinsic and meaningful interpretability.
Comments16 pages, 8 figures, 13 tables
