arXiv 2511.187832025-11-24cs.LGcs.SI

超图对比学习：适用于同质和异质超图的框架

Hypergraph Contrastive Learning for both Homophilic and Heterophilic Hypergraphs

College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；School of Mathematical and Computer Sciences, Heriot-Watt University（赫瑞斯泰大学数学与计算机科学学院）；Department of Information Engineering and Computer Science, University of Trento（特伦托大学信息工程与计算机科学系）

Renchu Guan, Xuyang Li, Yachao Zhang, Wei Pang, Fausto Giunchiglia, Ximing Li, Yonghao Liu, Xiaoyue Feng

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

HONOR提出一种适用于同质和异质超图的对比学习框架，通过两种互补机制提升超边和节点表示的判别性和鲁棒性。

摘要：

超图作为传统图的推广，自然捕捉高阶关系。近年来，超图神经网络（HNNs）被广泛用于捕捉复杂的高阶关系。然而，大多数现有的超图神经网络方法本质上依赖同质性假设，这在现实世界中并不总是成立，因为现实场景中存在显著的异质结构。为了解决这一限制，我们提出了HONOR，一种新的无监督超图对比学习框架，适用于同质和异质超图。具体来说，HONOR通过两种互补的机制显式建模超边和节点之间的异质关系：基于提示的超边特征构建策略，该策略在保持全局语义一致性的同时抑制局部噪声；以及自适应注意力聚合模块，该模块动态捕捉节点对超边的多样化局部贡献。结合高通滤波，这些设计使HONOR能够充分利用异质连接模式，产生更具判别性和鲁棒性的节点和超边表示。理论上，我们展示了HONOR的优越泛化能力和鲁棒性。实验上，广泛实验进一步验证了HONOR在同质和异质数据集上均优于现有最先进的基线。

英文摘要：

Hypergraphs, as a generalization of traditional graphs, naturally capture high-order relationships. In recent years, hypergraph neural networks (HNNs) have been widely used to capture complex high-order relationships. However, most existing hypergraph neural network methods inherently rely on the homophily assumption, which often does not hold in real-world scenarios that exhibit significant heterophilic structures. To address this limitation, we propose \textbf{HONOR}, a novel unsupervised \textbf{H}ypergraph c\textbf{ON}trastive learning framework suitable for both hom\textbf{O}philic and hete\textbf{R}ophilic hypergraphs. Specifically, HONOR explicitly models the heterophilic relationships between hyperedges and nodes through two complementary mechanisms: a prompt-based hyperedge feature construction strategy that maintains global semantic consistency while suppressing local noise, and an adaptive attention aggregation module that dynamically captures the diverse local contributions of nodes to hyperedges. Combined with high-pass filtering, these designs enable HONOR to fully exploit heterophilic connection patterns, yielding more discriminative and robust node and hyperedge representations. Theoretically, we demonstrate the superior generalization ability and robustness of HONOR. Empirically, extensive experiments further validate that HONOR consistently outperforms state-of-the-art baselines under both homophilic and heterophilic datasets.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。