RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
arXiv:1902.10197
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 (100)
- Learning Intents behind Interactions with Knowledge Graph for Recommendation
- Composition-based Multi-Relational Graph Convolutional Networks
- Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings
- TransGCN:Coupling Transformation Assumptions with Graph Convolutional Networks for Link Prediction
- Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs
- Inductive Relation Prediction by Subgraph Reasoning
- Trans4E: Link Prediction on Scholarly Knowledge Graphs
- HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph
- Prototypical Representation Learning for Relation Extraction
- Efficient Probabilistic Logic Reasoning with Graph Neural Networks
- Few-shot link prediction via graph neural networks for Covid-19 drug-repurposing
- Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
- Understanding Negative Sampling in Graph Representation Learning
- Cognitive Knowledge Graph Reasoning for One-shot Relational Learning
- CoLAKE: Contextualized Language and Knowledge Embedding
- Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation
- xERTE: Explainable Reasoning on Temporal Knowledge Graphs for Forecasting Future Links
- A Survey on Graph Neural Networks for Knowledge Graph Completion
- r-GAT: Relational Graph Attention Network for Multi-Relational Graphs
- Probability Calibration for Knowledge Graph Embedding Models
- Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning
- Scientific Language Models for Biomedical Knowledge Base Completion: An Empirical Study
- Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs
- Learn to Explain Efficiently via Neural Logic Inductive Learning
- Repurpose Open Data to Discover Therapeutics for COVID-19 using Deep Learning
- Graph Neural Pre-training for Enhancing Recommendations using Side Information
- QuatDE: Dynamic Quaternion Embedding for Knowledge Graph Completion
- Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning
- Path-Enhanced Multi-Relational Question Answering with Knowledge Graph Embeddings
- Role-Aware Modeling for N-ary Relational Knowledge Bases
- Logic Embeddings for Complex Query Answering
- Biomedical Knowledge Graph Refinement with Embedding and Logic Rules
- SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs
- Utilising Graph Machine Learning within Drug Discovery and Development
- AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding
- A Survey of Knowledge Graph Embedding and Their Applications
- Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph
- Learning Collaborative Agents with Rule Guidance for Knowledge Graph Reasoning
- Link Prediction on N-ary Relational Facts: A Graph-based Approach
- Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding
- DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion
- Relation-weighted Link Prediction for Disease Gene Identification
- Efficient Relation-aware Scoring Function Search for Knowledge Graph Embedding
- EAGER: Embedding-Assisted Entity Resolution for Knowledge Graphs
- Node Classification Meets Link Prediction on Knowledge Graphs
- EchoEA: Echo Information between Entities and Relations for Entity Alignment
- Predicting affinity ties in a surname network
- Knowledge Graph Embedding with Atrous Convolution and Residual Learning
- Temporal Knowledge Graph Reasoning Triggered by Memories
- Learning Embeddings from Knowledge Graphs With Numeric Edge Attributes
- Searching to Sparsify Tensor Decomposition for N-ary Relational Data
- Representation Learning with Ordered Relation Paths for Knowledge Graph Completion
- Out-of-Vocabulary Entities in Link Prediction
- Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs
- Neural Entity Summarization with Joint Encoding and Weak Supervision
- Personalized Entity Resolution with Dynamic Heterogeneous Knowledge Graph Representations
- Edge: Enriching Knowledge Graph Embeddings with External Text
- Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning
- Switch Spaces: Learning Product Spaces with Sparse Gating
- Benchmark and Best Practices for Biomedical Knowledge Graph Embeddings
- Software Engineering Event Modeling using Relative Time in Temporal Knowledge Graphs
- NASE: Learning Knowledge Graph Embedding for Link Prediction via Neural Architecture Search
- Disentangle-based Continual Graph Representation Learning
- Inductively Representing Out-of-Knowledge-Graph Entities by Optimal Estimation Under Translational Assumptions
- Context-aware Entity Typing in Knowledge Graphs
- HeMI: Multi-view Embedding in Heterogeneous Graphs
- Embedding Heterogeneous Networks into Hyperbolic Space Without Meta-path
- Decompressing Knowledge Graph Representations for Link Prediction
- TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphs
- OntoZSL: Ontology-enhanced Zero-shot Learning
- SEEK: Segmented Embedding of Knowledge Graphs
- Video Captioning Using Weak Annotation
- TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting
- CollaborER: A Self-supervised Entity Resolution Framework Using Multi-features Collaboration
- Combining Rules and Embeddings via Neuro-Symbolic AI for Knowledge Base Completion
- HopfE: Knowledge Graph Representation Learning using Inverse Hopf Fibrations
- LightCAKE: A Lightweight Framework for Context-Aware Knowledge Graph Embedding
- PPKE: Knowledge Representation Learning by Path-based Pre-training
- Is There More Pattern in Knowledge Graph? Exploring Proximity Pattern for Knowledge Graph Embedding
- A Data-Driven Study of Commonsense Knowledge using the ConceptNet Knowledge Base
- Augmenting the User-Item Graph with Textual Similarity Models
- Rule-Guided Graph Neural Networks for Recommender Systems
- Open Knowledge Enrichment for Long-tail Entities
- NOTE: Solution for KDD-CUP 2021 WikiKG90M-LSC
- A Probabilistic Framework for Knowledge Graph Data Augmentation
- HYPER^2: Hyperbolic Poincare Embedding for Hyper-Relational Link Prediction
- Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset
- Quantifying Similarity between Relations with Fact Distribution
- Are Missing Links Predictable? An Inferential Benchmark for Knowledge Graph Completion
- Technical Report of Team GraphMIRAcles in the WikiKG90M-LSC Track of OGB-LSC @ KDD Cup 2021
- A Literature Review of Recent Graph Embedding Techniques for Biomedical Data
- Wikidated 1.0: An Evolving Knowledge Graph Dataset of Wikidata's Revision History
- Addressing Class-Imbalance Problem in Personalized Ranking
- Using Pairwise Occurrence Information to Improve Knowledge Graph Completion on Large-Scale Datasets
- A Systematic Investigation of KB-Text Embedding Alignment at Scale
- Representing Syntax and Composition with Geometric Transformations
- Exploring Effects of Random Walk Based Minibatch Selection Policy on Knowledge Graph Completion
- NePTuNe: Neural Powered Tucker Network for Knowledge Graph Completion
- Biomedical Information Extraction for Disease Gene Prioritization
- Fact Checking via Path Embedding and Aggregation