HyBridge：桥接引导的双曲超图自监督表示学习框架
HyBridge: Bridge-Guided Self-Supervised Hyperbolic Hypergraph Representation Learning
AI 导读
论文提出 HyBridge，一个自监督双曲超图表示学习框架，通过基于超边外部连接性估计节点桥接分数、双曲超图编码、按桥接分数引导节点径向位置，并用对比学习保持节点判别性。在 10 个真实超图上的实验显示，其优于 22 种对比方法，节点分类最高提升 9.82%，代码已开源。
正文 · 原文
Abstract:Hypergraphs capture groupwise relationships among multiple nodes and often exhibit tree-like structures. Although hyperbolic space is well suited for modeling such structures, simply extending existing hypergraph representation learning (HRL) methods to hyperbolic space does not consistently improve performance. In this paper, we investigate the relationship between node structural properties and hyperbolic embedding radii and find that bridge nodes tend to lie closer to the center in graphs, whereas this relationship is not consistently observed in hypergraphs. We further find that conventional bridge score estimation may fail to capture the groupwise connectivity of hypergraphs. Motivated by these findings, we propose HyBridge, a self-supervised hyperbolic HRL framework that (1) estimates node bridge scores by considering the external connectivity of individual hyperedges, (2) learns node and hyperedge embeddings through hyperbolic hypergraph encoding, (3) guides node radial positions according to their bridge scores, and (4) employs contrastive learning to preserve node discriminability. Extensive experiments on 10 real-world hypergraphs demonstrate that HyBridge outperforms 22 competing methods, achieving performance improvements of up to 9.82% in node classification. For reproducibility, we provide the code at this https URL.
| Subjects: | Social and Information Networks (cs.SI); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.16351 [cs.SI] |
| (or arXiv:2611.16351v1 [cs.SI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.16351 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: David Yoon Suk Kang [view email]
[v1]
Thu, 12 Nov 2026 06:10:00 UTC (455 KB)
来源：arXiv cs.AI · arxiv.org