提出GCAT模型，用注意力机制提升知识图谱链接预测效果
Graph Collaborative Attention Network for Link Prediction in Knowledge Graphs
- 用多头注意力融合实体与关系特征，增强局部邻域信息聚合
- 在4个基准数据集上超越规则方法，达到或超过现有神经模型表现
- 适合研究知识图谱补全、图神经网络的读者参考
知识图谱以结构化方式表示现实世界实体及其关系，广泛应用于信息检索与自动推理。本文系统比较了传统基于规则的方法与现代深度学习方法在链接预测中的表现。聚焦于KBGAT这一图神经网络模型，其利用多头注意力机制联合编码实体与关系特征。为推进该方向，我们提出改进模型GCAT（Graph Collaborative Attention Network），通过增强异构节点间的上下文聚合与交互能力。在四个常用基准数据集上的实验表明，GCAT不仅持续优于规则方法，还实现了与现有神经嵌入模型相当或更优的性能。结果凸显了基于注意力架构在捕捉复杂关系模式方面的优势，适用于知识图谱补全任务。
原文摘要 · Abstract (English)
Knowledge graphs offer a structured representation of real-world entities and their relationships, enabling a wide range of applications from information retrieval to automated reasoning. In this paper, we conduct a systematic comparison between traditional rule-based approaches and modern deep learning methods for link prediction. We focus on KBGAT, a graph neural network model that leverages multi-head attention to jointly encode both entity and relation features within local neighborhood structures. To advance this line of research, we introduce \textbf{GCAT} (Graph Collaborative Attention Network), a refined model that enhances context aggregation and interaction between heterogeneous nodes. Experimental results on four widely-used benchmark datasets demonstrate that GCAT not only consistently outperforms rule-based methods but also achieves competitive or superior performance compared to existing neural embedding models. Our findings highlight the advantages of attention-based architectures in capturing complex relational patterns for knowledge graph completion tasks.
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。