PPKE: Knowledge Representation Learning by Path-based Pre-training
arXiv:2012.03573
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.
References in corpus (8)
- A Survey on Knowledge Graphs: Representation, Acquisition and Applications
- Complex Embeddings for Simple Link Prediction
- A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
- RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
- ProjE: Embedding Projection for Knowledge Graph Completion
- Modeling Relation Paths for Representation Learning of Knowledge Bases
- CoKE: Contextualized Knowledge Graph Embedding
- A Re-evaluation of Knowledge Graph Completion Methods