Enhancing Heterogeneous Knowledge Graph Completion with a Novel GAT-based Approach

TL;DR

This paper introduces GATH, a novel GAT-based method for heterogeneous knowledge graph completion that addresses overfitting and class imbalance issues, significantly improving prediction accuracy on benchmark datasets.

Contribution

GATH incorporates dual attention modules and new encoding techniques to enhance heterogeneous KG completion, overcoming overfitting and imbalance challenges.

Findings

GATH outperforms existing models on Hits@10 and MRR metrics.

GATH achieves 5.2% improvements on FB15K-237.

GATH achieves 14.6% improvements on WN18RR.

Abstract

Knowledge graphs (KGs) play a vital role in enhancing search results and recommendation systems. With the rapid increase in the size of the KGs, they are becoming inaccuracy and incomplete. This problem can be solved by the knowledge graph completion methods, of which graph attention network (GAT)-based methods stand out since their superior performance. However, existing GAT-based knowledge graph completion methods often suffer from overfitting issues when dealing with heterogeneous knowledge graphs, primarily due to the unbalanced number of samples. Additionally, these methods demonstrate poor performance in predicting the tail (head) entity that shares the same relation and head (tail) entity with others. To solve these problems, we propose GATH, a novel GAT-based method designed for Heterogeneous KGs. GATH incorporates two separate attention network modules that work synergistically to predict the missing entities. We also introduce novel encoding and feature transformation approaches, enabling the robust performance of GATH in scenarios with imbalanced samples. Comprehensive experiments are conducted to evaluate the GATH's performance. Compared with the existing SOTA GAT-based model on Hits@10 and MRR metrics, our model improves performance by 5.2% and 5.2% on the FB15K-237 dataset, and by 4.5% and 14.6% on the WN18RR dataset, respectively.