DisenE: Disentangling Knowledge Graph Embeddings

TL;DR

DisenE is a novel framework for learning interpretable, disentangled knowledge graph embeddings using attention mechanisms and regularizers, improving link prediction performance.

Contribution

It introduces an end-to-end disentanglement approach with attention and regularizers, enhancing interpretability and effectiveness of knowledge graph embeddings.

Findings

DisenE improves link prediction accuracy.

It enhances interpretability of entity representations.

DisenE outperforms existing models in experiments.

Abstract

Knowledge graph embedding (KGE), aiming to embed entities and relations into low-dimensional vectors, has attracted wide attention recently. However, the existing research is mainly based on the black-box neural models, which makes it difficult to interpret the learned representation. In this paper, we introduce DisenE, an end-to-end framework to learn disentangled knowledge graph embeddings. Specially, we introduce an attention-based mechanism that enables the model to explicitly focus on relevant components of entity embeddings according to a given relation. Furthermore, we introduce two novel regularizers to encourage each component of the entity representation to independently reflect an isolated semantic aspect. Experimental results demonstrate that our proposed DisenE investigates a perspective to address the interpretability of KGE and is proved to be an effective way to improve the performance of link prediction tasks.