DisenKGAT: Knowledge Graph Embedding with Disentangled Graph Attention Network

TL;DR

DisenKGAT introduces a novel disentangled attention network for knowledge graph completion, enhancing relation modeling with micro- and macro-disentanglement to improve accuracy and explainability.

Contribution

The paper proposes a new disentangled attention mechanism for KGC that captures complex relations more effectively than previous static models.

Findings

Outperforms existing methods in accuracy on benchmark datasets.

Demonstrates improved explainability of learned representations.

Shows robustness across various score functions.

Abstract

Knowledge graph completion (KGC) has become a focus of attention across deep learning community owing to its excellent contribution to numerous downstream tasks. Although recently have witnessed a surge of work on KGC, they are still insufficient to accurately capture complex relations, since they adopt the single and static representations. In this work, we propose a novel Disentangled Knowledge Graph Attention Network (DisenKGAT) for KGC, which leverages both micro-disentanglement and macro-disentanglement to exploit representations behind Knowledge graphs (KGs). To achieve micro-disentanglement, we put forward a novel relation-aware aggregation to learn diverse component representation. For macro-disentanglement, we leverage mutual information as a regularization to enhance independence. With the assistance of disentanglement, our model is able to generate adaptive representations in terms of the given scenario. Besides, our work has strong robustness and flexibility to adapt to various score functions. Extensive experiments on public benchmark datasets have been conducted to validate the superiority of DisenKGAT over existing methods in terms of both accuracy and explainability.