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 (197)
- A Survey on Knowledge Graphs: Representation, Acquisition and Applications
- Knowledge Graphs
- MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding
- Learning Intents behind Interactions with Knowledge Graph for Recommendation
- Open Graph Benchmark: Datasets for Machine Learning on Graphs
- KG-BERT: BERT for Knowledge Graph Completion
- Quaternion Knowledge Graph Embeddings
- A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs
- Hypernetwork Knowledge Graph Embeddings
- Composition-based Multi-Relational Graph Convolutional Networks
- Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework
- OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs
- Semantic Models for the First-stage Retrieval: A Comprehensive Review
- Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
- Probabilistic Logic Neural Networks for Reasoning
- Knowledge Graph informed Fake News Classification via Heterogeneous Representation Ensembles
- RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs
- KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation
- TransGCN:Coupling Transformation Assumptions with Graph Convolutional Networks for Link Prediction
- Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings
- Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs
- CoKE: Contextualized Knowledge Graph Embedding
- DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks
- Understanding the Performance of Knowledge Graph Embeddings in Drug Discovery
- Inductive Relation Prediction by Subgraph Reasoning
- Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs
- Trans4E: Link Prediction on Scholarly Knowledge Graphs
- ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs
- HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph
- Continuous Graph Neural Networks
- Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion
- Prototypical Representation Learning for Relation Extraction
- Efficient Probabilistic Logic Reasoning with Graph Neural Networks
- Temporal Knowledge Graph Embedding Model based on Additive Time Series Decomposition
- Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs
- Few-shot link prediction via graph neural networks for Covid-19 drug-repurposing
- Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
- Multi-relational Poincaré Graph Embeddings
- Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark
- LineaRE: Simple but Powerful Knowledge Graph Embedding for Link Prediction
- BoxE: A Box Embedding Model for Knowledge Base Completion
- Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction
- Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
- Enhancing Heterogeneous Knowledge Graph Completion with a Novel GAT-based Approach
- Understanding Negative Sampling in Graph Representation Learning
- Cognitive Knowledge Graph Reasoning for One-shot Relational Learning
- Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion
- Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation
- HyperKG: Hyperbolic Knowledge Graph Embeddings for Knowledge Base Completion
- CoLAKE: Contextualized Language and Knowledge Embedding
- GripNet: Graph Information Propagation on Supergraph for Heterogeneous Graphs
- xERTE: Explainable Reasoning on Temporal Knowledge Graphs for Forecasting Future Links
- A Survey on Graph Neural Networks for Knowledge Graph Completion
- PairRE: Knowledge Graph Embeddings via Paired Relation Vectors
- r-GAT: Relational Graph Attention Network for Multi-Relational Graphs
- Probability Calibration for Knowledge Graph Embedding Models
- Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding
- Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning
- Triple Classification for Scholarly Knowledge Graph Completion
- Counterfactual Learning on Graphs: A Survey
- How Knowledge Graph and Attention Help? A Quantitative Analysis into Bag-level Relation Extraction
- Scientific Language Models for Biomedical Knowledge Base Completion: An Empirical Study
- NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs
- Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs
- Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study
- Neural Graph Embedding Methods for Natural Language Processing
- Measuring Social Bias in Knowledge Graph Embeddings
- Learn to Explain Efficiently via Neural Logic Inductive Learning
- TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation
- DHGE: Dual-View Hyper-Relational Knowledge Graph Embedding for Link Prediction and Entity Typing
- Unified Interpretation of Softmax Cross-Entropy and Negative Sampling: With Case Study for Knowledge Graph Embedding
- Repurpose Open Data to Discover Therapeutics for COVID-19 using Deep Learning
- Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding
- QuatDE: Dynamic Quaternion Embedding for Knowledge Graph Completion
- Modeling relation paths for knowledge base completion via joint adversarial training
- Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion
- Towards Learning Instantiated Logical Rules from Knowledge Graphs
- AutoSF: Searching Scoring Functions for Knowledge Graph Embedding
- Path-Enhanced Multi-Relational Question Answering with Knowledge Graph Embeddings
- FedE: Embedding Knowledge Graphs in Federated Setting
- Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning
- MDE: Multiple Distance Embeddings for Link Prediction in Knowledge Graphs
- Graph Neural Pre-training for Enhancing Recommendations using Side Information
- Logic Embeddings for Complex Query Answering
- Role-Aware Modeling for N-ary Relational Knowledge Bases
- Biomedical Knowledge Graph Refinement with Embedding and Logic Rules
- SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs
- Adaptive Attentional Network for Few-Shot Knowledge Graph Completion
- Relational Message Passing for Knowledge Graph Completion
- Utilising Graph Machine Learning within Drug Discovery and Development
- Knowledge Base Completion: Baseline strikes back (Again)
- A Re-evaluation of Knowledge Graph Completion Methods
- Joint Embedding Learning of Educational Knowledge Graphs
- AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding
- SAFRAN: An interpretable, rule-based link prediction method outperforming embedding models
- Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding
- CogDL: A Comprehensive Library for Graph Deep Learning
- A Survey of Knowledge Graph Embedding and Their Applications
- Link Prediction on N-ary Relational Facts: A Graph-based Approach
- Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph
- Learning Collaborative Agents with Rule Guidance for Knowledge Graph Reasoning
- Seeing is Knowing! Fact-based Visual Question Answering using Knowledge Graph Embeddings
- Efficient, Simple and Automated Negative Sampling for Knowledge Graph Embedding
- EchoEA: Echo Information between Entities and Relations for Entity Alignment
- An Adversarial Transfer Network for Knowledge Representation Learning
- Knowledge Graph Embedding with Atrous Convolution and Residual Learning
- Out-of-Sample Representation Learning for Multi-Relational Graphs
- EAGER: Embedding-Assisted Entity Resolution for Knowledge Graphs
- Predicting affinity ties in a surname network
- DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion
- Node Classification Meets Link Prediction on Knowledge Graphs
- Collaborative Policy Learning for Open Knowledge Graph Reasoning
- Relation-weighted Link Prediction for Disease Gene Identification
- Group Representation Theory for Knowledge Graph Embedding
- Efficient Relation-aware Scoring Function Search for Knowledge Graph Embedding
- Learning Embeddings from Knowledge Graphs With Numeric Edge Attributes
- Type-augmented Relation Prediction in Knowledge Graphs
- Inductive Learning on Commonsense Knowledge Graph Completion
- Multi-Partition Embedding Interaction with Block Term Format for Knowledge Graph Completion
- Drug-Drug Interaction Prediction with Wasserstein Adversarial Autoencoder-based Knowledge Graph Embeddings
- Cross-lingual Entity Alignment with Incidental Supervision
- Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs
- Out-of-Vocabulary Entities in Link Prediction
- Temporal Knowledge Graph Reasoning Triggered by Memories
- Relation Adversarial Network for Low Resource Knowledge Graph Completion
- Searching to Sparsify Tensor Decomposition for N-ary Relational Data
- Representation Learning with Ordered Relation Paths for Knowledge Graph Completion
- Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
- Unit Ball Model for Embedding Hierarchical Structures in the Complex Hyperbolic Space
- Convolutional Hypercomplex Embeddings for Link Prediction
- TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphs
- Decompressing Knowledge Graph Representations for Link Prediction
- Software Engineering Event Modeling using Relative Time in Temporal Knowledge Graphs
- Context-aware Entity Typing in Knowledge Graphs
- NASE: Learning Knowledge Graph Embedding for Link Prediction via Neural Architecture Search
- HeMI: Multi-view Embedding in Heterogeneous Graphs
- Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning
- Disentangle-based Continual Graph Representation Learning
- Inductively Representing Out-of-Knowledge-Graph Entities by Optimal Estimation Under Translational Assumptions
- Switch Spaces: Learning Product Spaces with Sparse Gating
- Edge: Enriching Knowledge Graph Embeddings with External Text
- KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization and Completion
- Personalized Entity Resolution with Dynamic Heterogeneous Knowledge Graph Representations
- Embedding Heterogeneous Networks into Hyperbolic Space Without Meta-path
- Neural Entity Summarization with Joint Encoding and Weak Supervision
- Benchmark and Best Practices for Biomedical Knowledge Graph Embeddings
- Highly Efficient Knowledge Graph Embedding Learning with Orthogonal Procrustes Analysis
- Improving Conversational Recommendation System by Pretraining on Billions Scale of Knowledge Graph
- A Data-Driven Study of Commonsense Knowledge using the ConceptNet Knowledge Base
- NOTE: Solution for KDD-CUP 2021 WikiKG90M-LSC
- HopfE: Knowledge Graph Representation Learning using Inverse Hopf Fibrations
- CollaborER: A Self-supervised Entity Resolution Framework Using Multi-features Collaboration
- TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting
- Combining Rules and Embeddings via Neuro-Symbolic AI for Knowledge Base Completion
- Augmenting the User-Item Graph with Textual Similarity Models
- Is There More Pattern in Knowledge Graph? Exploring Proximity Pattern for Knowledge Graph Embedding
- Text-guided Legal Knowledge Graph Reasoning
- Open Knowledge Enrichment for Long-tail Entities
- PPKE: Knowledge Representation Learning by Path-based Pre-training
- Knowledge Graph Embeddings in Geometric Algebras
- RTFE: A Recursive Temporal Fact Embedding Framework for Temporal Knowledge Graph Completion
- Knowledge Embedding Based Graph Convolutional Network
- OntoZSL: Ontology-enhanced Zero-shot Learning
- LightCAKE: A Lightweight Framework for Context-Aware Knowledge Graph Embedding
- SEEK: Segmented Embedding of Knowledge Graphs
- Video Captioning Using Weak Annotation
- Rule-Guided Graph Neural Networks for Recommender Systems
- HittER: Hierarchical Transformers for Knowledge Graph Embeddings
- Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer
- NePTuNe: Neural Powered Tucker Network for Knowledge Graph Completion
- HYPER^2: Hyperbolic Poincare Embedding for Hyper-Relational Link Prediction
- RatE: Relation-Adaptive Translating Embedding for Knowledge Graph Completion
- Fact Checking via Path Embedding and Aggregation
- NegatER: Unsupervised Discovery of Negatives in Commonsense Knowledge Bases
- Biomedical Information Extraction for Disease Gene Prioritization
- Exploring Effects of Random Walk Based Minibatch Selection Policy on Knowledge Graph Completion
- A Statistical Relational Approach to Learning Distance-based GCNs
- Within-Document Event Coreference with BERT-Based Contextualized Representations
- Hyperbolic Geometry is Not Necessary: Lightweight Euclidean-Based Models for Low-Dimensional Knowledge Graph Embeddings
- Addressing Class-Imbalance Problem in Personalized Ranking
- Case-based Reasoning for Natural Language Queries over Knowledge Bases
- Using Pairwise Occurrence Information to Improve Knowledge Graph Completion on Large-Scale Datasets
- CEAR: Cross-Entity Aware Reranker for Knowledge Base Completion
- A Probabilistic Framework for Knowledge Graph Data Augmentation
- Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset
- Knowledge Sheaves: A Sheaf-Theoretic Framework for Knowledge Graph Embedding
- Towards Robust Knowledge Graph Embedding via Multi-task Reinforcement Learning
- Link Analysis meets Ontologies: Are Embeddings the Answer?
- Representing Syntax and Composition with Geometric Transformations
- A Systematic Investigation of KB-Text Embedding Alignment at Scale
- Narrative Cartography with Knowledge Graphs
- 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
- Wikidated 1.0: An Evolving Knowledge Graph Dataset of Wikidata's Revision History
- Quantifying Similarity between Relations with Fact Distribution
- Regex Queries over Incomplete Knowledge Bases
- A Literature Review of Recent Graph Embedding Techniques for Biomedical Data