用多个双曲空间更好捕捉异质图的复杂结构
Multi-Hyperbolic Space-based Heterogeneous Graph Attention Network
- 引入多双曲空间建模异质图中不同的幂律结构
- 在多个任务上优于现有最先进模型
- 适合处理具有层次和幂律特性的异质图数据
为利用异质图中的复杂结构，近期研究采用双曲空间（具有恒定负曲率和指数增长空间）进行异质图嵌入，因其与异质图的结构特性相符。然而，尽管异质图天然存在多种幂律结构，大多数双曲异质图嵌入模型仅使用单一双曲空间表示整个图，难以有效捕捉图内多样化的幂律结构。为此，我们提出多双曲空间异质图注意力网络(MSGAT)，通过多个双曲空间更有效地建模异质图中的多样化幂律结构。我们在多个图机器学习任务上进行了全面实验，结果表明，MSGAT在各项任务中均优于现有最先进基线方法，能有效捕捉异质图的复杂结构。
原文摘要 · Abstract (English)
To leverage the complex structures within heterogeneous graphs, recent studies on heterogeneous graph embedding use a hyperbolic space, characterized by a constant negative curvature and exponentially increasing space, which aligns with the structural properties of heterogeneous graphs. However, despite heterogeneous graphs inherently possessing diverse power-law structures, most hyperbolic heterogeneous graph embedding models use a single hyperbolic space for the entire heterogeneous graph, which may not effectively capture the diverse power-law structures within the heterogeneous graph. To address this limitation, we propose Multi-hyperbolic Space-based heterogeneous Graph Attention Network (MSGAT), which uses multiple hyperbolic spaces to effectively capture diverse power-law structures within heterogeneous graphs. We conduct comprehensive experiments to evaluate the effectiveness of MSGAT. The experimental results demonstrate that MSGAT outperforms state-of-the-art baselines in various graph machine learning tasks, effectively capturing the complex structures of heterogeneous graphs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。