RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space

Abstract

We study the problem of learning representations of entities and relations in knowledge graphs for predicting missing links. The success of such a task heavily relies on the ability of modeling and inferring the patterns of (or between) the relations. In this paper, we present a new approach for knowledge graph embedding called RotatE, which is able to model and infer various relation patterns including: symmetry/antisymmetry, inversion, and composition. Specifically, the RotatE model defines each relation as a rotation from the source entity to the target entity in the complex vector space. In addition, we propose a novel self-adversarial negative sampling technique for efficiently and effectively training the RotatE model. Experimental results on multiple benchmark knowledge graphs show that the proposed RotatE model is not only scalable, but also able to infer and model various relation patterns and significantly outperform existing state-of-the-art models for link prediction.

Accepted to ICLR 2019

Cited by in corpus (29)

• Composition-based Multi-Relational Graph Convolutional Networks
• TransGCN:Coupling Transformation Assumptions with Graph Convolutional Networks for Link Prediction
• Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings
• Inductive Relation Prediction by Subgraph Reasoning
• Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs
• Efficient Probabilistic Logic Reasoning with Graph Neural Networks
• Few-shot link prediction via graph neural networks for Covid-19 drug-repurposing
• Cognitive Knowledge Graph Reasoning for One-shot Relational Learning
• Understanding Negative Sampling in Graph Representation Learning
• CoLAKE: Contextualized Language and Knowledge Embedding
• Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation
• A Survey on Graph Neural Networks for Knowledge Graph Completion
• Probability Calibration for Knowledge Graph Embedding Models
• Learn to Explain Efficiently via Neural Logic Inductive Learning
• Repurpose Open Data to Discover Therapeutics for COVID-19 using Deep Learning
• AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding
• Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph
• Representation Learning with Ordered Relation Paths for Knowledge Graph Completion
• Software Engineering Event Modeling using Relative Time in Temporal Knowledge Graphs
• Decompressing Knowledge Graph Representations for Link Prediction
• NASE: Learning Knowledge Graph Embedding for Link Prediction via Neural Architecture Search
• Benchmark and Best Practices for Biomedical Knowledge Graph Embeddings
• Inductively Representing Out-of-Knowledge-Graph Entities by Optimal Estimation Under Translational Assumptions
• Open Knowledge Enrichment for Long-tail Entities
• Video Captioning Using Weak Annotation
• SEEK: Segmented Embedding of Knowledge Graphs
• Rule-Guided Graph Neural Networks for Recommender Systems
• Using Pairwise Occurrence Information to Improve Knowledge Graph Completion on Large-Scale Datasets
• Quantifying Similarity between Relations with Fact Distribution