arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2508.03280cs.LGcs.CLcs.SI
收藏

理解超关系知识图谱上的嵌入模型

Understanding the Embedding Models on Hyper-relational Knowledge Graph

Southeast University(东南大学);The Hong Kong Polytechnic University(香港理工大学);Tencent(腾讯)

Yubo Wang, Shimin Di, Zhili Wang, Haoyang Li, Fei Teng, Hao Xin, Lei Chen

AI总结:

本文通过分解方法评估经典KGE模型在超关系知识图谱上的表现,发现其可与专用模型媲美,并揭示现有HKGE模型的不足,进而提出FormerGNN框架以保留拓扑、捕获长程依赖并整合信息,实验证明其性能优越。

摘要:

近年来,超关系知识图谱(HKGs)被提出作为传统知识图谱(KGs)的扩展,以更好地表示带有额外限定符的真实世界事实。因此,研究人员试图通过设计额外的限定符处理模块,将经典的知识图谱嵌入(KGE)模型适配到HKGs上。然而,目前尚不清楚超关系知识图谱嵌入(HKGE)模型的优越性能是源于其基础KGE模型还是专门设计的扩展模块。因此,在本文中,我们使用三种分解方法从数据角度将HKGs转换为KG格式,并评估了几种经典KGE模型在HKGs上的性能。我们的结果表明,一些KGE模型达到了与HKGE模型相当的性能。进一步分析后,我们发现分解方法改变了原始HKG拓扑结构,未能完全保留HKG信息。此外,我们观察到当前的HKGE模型要么在捕获图的长程依赖性方面不足,要么由于信息压缩问题而难以整合主三元组和限定符信息。为了进一步验证我们的发现并为未来的HKGE研究提供潜在方向,我们提出了FormerGNN框架。该框架采用限定符整合器来保留原始HKG拓扑结构,并采用基于GNN的图编码器来捕获图的长程依赖性,随后通过一种改进的方法整合主三元组和限定符信息以缓解压缩问题。我们的实验结果表明,FormerGNN优于现有的HKGE模型。

英文摘要:

Recently, Hyper-relational Knowledge Graphs (HKGs) have been proposed as an extension of traditional Knowledge Graphs (KGs) to better represent real-world facts with additional qualifiers. As a result, researchers have attempted to adapt classical Knowledge Graph Embedding (KGE) models for HKGs by designing extra qualifier processing modules. However, it remains unclear whether the superior performance of Hyper-relational KGE (HKGE) models arises from their base KGE model or the specially designed extension module. Hence, in this paper, we data-wise convert HKGs to KG format using three decomposition methods and then evaluate the performance of several classical KGE models on HKGs. Our results show that some KGE models achieve performance comparable to that of HKGE models. Upon further analysis, we find that the decomposition methods alter the original HKG topology and fail to fully preserve HKG information. Moreover, we observe that current HKGE models are either insufficient in capturing the graph's long-range dependency or struggle to integrate main-triple and qualifier information due to the information compression issue. To further justify our findings and offer a potential direction for future HKGE research, we propose the FormerGNN framework. This framework employs a qualifier integrator to preserve the original HKG topology, and a GNN-based graph encoder to capture the graph's long-range dependencies, followed by an improved approach for integrating main-triple and qualifier information to mitigate compression issues. Our experimental results demonstrate that FormerGNN outperforms existing HKGE models.

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。

↑