Graph Collaborative Attention Network for Link Prediction in Knowledge Graphs

TL;DR

This paper introduces GCAT, a novel attention-based graph neural network model that improves link prediction in knowledge graphs by effectively capturing complex relational patterns, outperforming traditional rule-based and existing neural methods.

Contribution

We propose GCAT, an advanced graph neural network with enhanced context aggregation and interaction capabilities for knowledge graph link prediction.

Findings

GCAT outperforms rule-based methods on benchmark datasets.

GCAT achieves competitive or superior results compared to existing neural models.

Attention mechanisms effectively capture complex relational patterns.

Abstract

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.