ProjE: Embedding Projection for Knowledge Graph Completion

Abstract

With the large volume of new information created every day, determining the validity of information in a knowledge graph and filling in its missing parts are crucial tasks for many researchers and practitioners. To address this challenge, a number of knowledge graph completion methods have been developed using low-dimensional graph embeddings. Although researchers continue to improve these models using an increasingly complex feature space, we show that simple changes in the architecture of the underlying model can outperform state-of-the-art models without the need for complex feature engineering. In this work, we present a shared variable neural network model called ProjE that fills-in missing information in a knowledge graph by learning joint embeddings of the knowledge graph's entities and edges, and through subtle, but important, changes to the standard loss function. In doing so, ProjE has a parameter size that is smaller than 11 out of 15 existing methods while performing $37\%$ better than the current-best method on standard datasets. We also show, via a new fact checking task, that ProjE is capable of accurately determining the veracity of many declarative statements.

14 pages, Accepted to AAAI 2017

Cited by in corpus (16)

• Multi-view Knowledge Graph Embedding for Entity Alignment
• Open-World Knowledge Graph Completion
• Knowledge Graph Embedding with Atrous Convolution and Residual Learning
• Relation-weighted Link Prediction for Disease Gene Identification
• Representation Learning with Ordered Relation Paths for Knowledge Graph Completion
• Augmenting and Tuning Knowledge Graph Embeddings
• TechKG: A Large-Scale Chinese Technology-Oriented Knowledge Graph
• TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphs
• Representation Learning in Heterogeneous Professional Social Networks with Ambiguous Social Connections
• SEEK: Segmented Embedding of Knowledge Graphs
• MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning
• PPKE: Knowledge Representation Learning by Path-based Pre-training
• Fact Checking via Path Embedding and Aggregation
• Link Prediction on N-ary Relational Data Based on Relatedness Evaluation
• Customized Graph Embedding: Tailoring Embedding Vectors to different Applications
• Integrating Approaches to Word Representation