Complex Embeddings for Simple Link Prediction

Abstract

In statistical relational learning, the link prediction problem is key to automatically understand the structure of large knowledge bases. As in previous studies, we propose to solve this problem through latent factorization. However, here we make use of complex valued embeddings. The composition of complex embeddings can handle a large variety of binary relations, among them symmetric and antisymmetric relations. Compared to state-of-the-art models such as Neural Tensor Network and Holographic Embeddings, our approach based on complex embeddings is arguably simpler, as it only uses the Hermitian dot product, the complex counterpart of the standard dot product between real vectors. Our approach is scalable to large datasets as it remains linear in both space and time, while consistently outperforming alternative approaches on standard link prediction benchmarks.

10+2 pages, accepted at ICML 2016

References in corpus (4)

• A Review of Relational Machine Learning for Knowledge Graphs
• Irreflexive and Hierarchical Relations as Translations
• Sign rank versus VC dimension
• Decomposing Real Square Matrices via Unitary Diagonalization

Cited by in corpus (131)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Knowledge Graphs
• Modeling polypharmacy side effects with graph convolutional networks
• A Survey of Fake News: Fundamental Theories, Detection Methods, and Opportunities
• A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
• Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences
• Translation-based Recommendation
• A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs
• Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion
• Hypernetwork Knowledge Graph Embeddings
• Drug Repurposing for COVID-19 via Knowledge Graph Completion
• SumGNN: Multi-typed Drug Interaction Prediction via Efficient Knowledge Graph Summarization
• Poincaré Embeddings for Learning Hierarchical Representations
• Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure
• Knowledge Graph Augmented Network Towards Multiview Representation Learning for Aspect-based Sentiment Analysis
• Neural Entity Linking: A Survey of Models Based on Deep Learning
• A Review of Biomedical Datasets Relating to Drug Discovery: A Knowledge Graph Perspective
• End-to-End Differentiable Proving
• A Review of Knowledge Graph Completion
• Knowledge Graph informed Fake News Classification via Heterogeneous Representation Ensembles
• From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer
• Modeling Relational Data with Graph Convolutional Networks
• Efficiently Embedding Dynamic Knowledge Graphs
• Representation Learning for Natural Language Processing
• TransGCN:Coupling Transformation Assumptions with Graph Convolutional Networks for Link Prediction
• An Open-World Extension to Knowledge Graph Completion Models
• KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completion
• Ontology-enhanced Prompt-tuning for Few-shot Learning
• Relation Embedding with Dihedral Group in Knowledge Graph
• Neighborhood Mixture Model for Knowledge Base Completion
• KBLRN : End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features
• HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph
• KBGAN: Adversarial Learning for Knowledge Graph Embeddings
• Mask and Reason: Pre-Training Knowledge Graph Transformers for Complex Logical Queries
• Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion
• DGL-KE: Training Knowledge Graph Embeddings at Scale
• Multi-Hop Knowledge Graph Reasoning with Reward Shaping
• Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs
• CORE: A Knowledge Graph Entity Type Prediction Method via Complex Space Regression and Embedding
• Ultrahyperbolic Knowledge Graph Embeddings
• Graph Collaborative Reasoning
• Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark
• LineaRE: Simple but Powerful Knowledge Graph Embedding for Link Prediction
• Link Prediction with Attention Applied on Multiple Knowledge Graph Embedding Models
• Knowledge Graph Embedding with Iterative Guidance from Soft Rules
• Geometric Algebra based Embeddings for Static and Temporal Knowledge Graph Completion
• Complex and Holographic Embeddings of Knowledge Graphs: A Comparison
• Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning
• Dynamic Parameter Allocation in Parameter Servers
• Adversarial Contrastive Estimation
• r-GAT: Relational Graph Attention Network for Multi-Relational Graphs
• Knowledge Graph Embedding with Entity Neighbors and Deep Memory Network
• One-Shot Relational Learning for Knowledge Graphs
• Improving Natural Language Inference Using External Knowledge in the Science Questions Domain
• DOLORES: Deep Contextualized Knowledge Graph Embeddings
• Towards Understanding Theoretical Advantages of Complex-Reaction Networks
• MöbiusE: Knowledge Graph Embedding on Möbius Ring
• Triple Classification for Scholarly Knowledge Graph Completion
• Knowledge Graph Embeddings and Explainable AI
• Interpreting Embedding Models of Knowledge Bases: A Pedagogical Approach
• Embedding and trajectories of temporal networks
• TorusE: Knowledge Graph Embedding on a Lie Group
• Advancing Biomedicine with Graph Representation Learning: Recent Progress, Challenges, and Future Directions
• LinkNBed: Multi-Graph Representation Learning with Entity Linkage
• Logic Attention Based Neighborhood Aggregation for Inductive Knowledge Graph Embedding
• Knowledge-driven Site Selection via Urban Knowledge Graph
• Zoo Guide to Network Embedding
• Unified Interpretation of Softmax Cross-Entropy and Negative Sampling: With Case Study for Knowledge Graph Embedding
• Composing Knowledge Graph Embeddings via Word Embeddings
• Modeling relation paths for knowledge base completion via joint adversarial training
• Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion
• SAppKG: Mobile App Recommendation Using Knowledge Graph and Side Information-A Secure Framework
• Benchmarking neural embeddings for link prediction in knowledge graphs under semantic and structural changes
• Adaptive Attentional Network for Few-Shot Knowledge Graph Completion
• Revisiting Simple Neural Networks for Learning Representations of Knowledge Graphs
• Event Prediction using Case-Based Reasoning over Knowledge Graphs
• Rule-Guided Compositional Representation Learning on Knowledge Graphs
• Role-Aware Modeling for N-ary Relational Knowledge Bases
• Relational Message Passing for Knowledge Graph Completion
• Source-Aware Embedding Training on Heterogeneous Information Networks
• On Evaluating Embedding Models for Knowledge Base Completion
• Few-Shot Knowledge Graph Completion
• Knowledge Base Completion: Baseline strikes back (Again)
• A Survey of Knowledge Graph Embedding and Their Applications
• Investigations on Knowledge Base Embedding for Relation Prediction and Extraction
• CogDL: A Comprehensive Library for Graph Deep Learning
• BOK-VQA: Bilingual outside Knowledge-Based Visual Question Answering via Graph Representation Pretraining
• The Tensor Brain: Semantic Decoding for Perception and Memory
• Semi-supervised Graph Embedding Approach to Dynamic Link Prediction
• An Adversarial Transfer Network for Knowledge Representation Learning
• Seeing is Knowing! Fact-based Visual Question Answering using Knowledge Graph Embeddings
• Comparing Aggregators for Relational Probabilistic Models
• Predicting affinity ties in a surname network
• EAGER: Embedding-Assisted Entity Resolution for Knowledge Graphs
• Path-Based Contextualization of Knowledge Graphs for Textual Entailment
• NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding
• Contextualized Knowledge-aware Attentive Neural Network: Enhancing Answer Selection with Knowledge
• Evaluating the Effectiveness of Margin Parameter when Learning Knowledge Embedding Representation for Domain-specific Multi-relational Categorized Data
• Embedding Uncertain Knowledge Graphs
• Binarized Knowledge Graph Embeddings
• Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning
• KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization and Completion
• Combining Axiom Injection and Knowledge Base Completion for Efficient Natural Language Inference
• Graph Pattern Entity Ranking Model for Knowledge Graph Completion
• NASE: Learning Knowledge Graph Embedding for Link Prediction via Neural Architecture Search
• A Physical Embedding Model for Knowledge Graphs
• Beyond Markov Logic: Efficient Mining of Prediction Rules in Large Graphs
• Embedding Cardinality Constraints in Neural Link Predictors
• Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts
• Augmenting the User-Item Graph with Textual Similarity Models
• Combining Rules and Embeddings via Neuro-Symbolic AI for Knowledge Base Completion
• MOHONE: Modeling Higher Order Network Effects in KnowledgeGraphs via Network Infused Embeddings
• MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning
• Recent Advances in Automated Question Answering In Biomedical Domain
• Good Intentions: Adaptive Parameter Management via Intent Signaling
• Neural Latent Relational Analysis to Capture Lexical Semantic Relations in a Vector Space
• PPKE: Knowledge Representation Learning by Path-based Pre-training
• Is There More Pattern in Knowledge Graph? Exploring Proximity Pattern for Knowledge Graph Embedding
• Principled Representation Learning for Entity Alignment
• What relations are reliably embeddable in Euclidean space?
• Fact Checking via Path Embedding and Aggregation
• Embedding Geographic Locations for Modelling the Natural Environment using Flickr Tags and Structured Data
• EM-RBR: a reinforced framework for knowledge graph completion from reasoning perspective
• Scalable knowledge base completion with superposition memories
• ACTC: Active Threshold Calibration for Cold-Start Knowledge Graph Completion
• Complex network prediction using deep learning
• A Comparative Study of Distributional and Symbolic Paradigms for Relational Learning
• Timestamping Documents and Beliefs
• Knowledge Graph Embedding Bi-Vector Models for Symmetric Relation
• Simple and Powerful Architecture for Inductive Recommendation Using Knowledge Graph Convolutions
• Why PairDiff works? -- A Mathematical Analysis of Bilinear Relational Compositional Operators for Analogy Detection