PPKE: Knowledge Representation Learning by Path-based Pre-training

TL;DR

PPKE introduces a path-based pre-training approach to enhance knowledge graph embeddings by leveraging complex multi-step relationships, significantly improving link and relation prediction accuracy.

Contribution

The paper proposes a novel path-based pre-training method, PPKE, that effectively incorporates graph contextual information into knowledge representation learning.

Findings

Achieves state-of-the-art results on benchmark datasets.

Improves link prediction and relation prediction tasks.

Demonstrates the effectiveness of graph contextual information integration.

Abstract

Entities may have complex interactions in a knowledge graph (KG), such as multi-step relationships, which can be viewed as graph contextual information of the entities. Traditional knowledge representation learning (KRL) methods usually treat a single triple as a training unit, and neglect most of the graph contextual information exists in the topological structure of KGs. In this study, we propose a Path-based Pre-training model to learn Knowledge Embeddings, called PPKE, which aims to integrate more graph contextual information between entities into the KRL model. Experiments demonstrate that our model achieves state-of-the-art results on several benchmark datasets for link prediction and relation prediction tasks, indicating that our model provides a feasible way to take advantage of graph contextual information in KGs.