Quaternion Knowledge Graph Embeddings

Abstract

In this work, we move beyond the traditional complex-valued representations, introducing more expressive hypercomplex representations to model entities and relations for knowledge graph embeddings. More specifically, quaternion embeddings, hypercomplex-valued embeddings with three imaginary components, are utilized to represent entities. Relations are modelled as rotations in the quaternion space. The advantages of the proposed approach are: (1) Latent inter-dependencies (between all components) are aptly captured with Hamilton product, encouraging a more compact interaction between entities and relations; (2) Quaternions enable expressive rotation in four-dimensional space and have more degree of freedom than rotation in complex plane; (3) The proposed framework is a generalization of ComplEx on hypercomplex space while offering better geometrical interpretations, concurrently satisfying the key desiderata of relational representation learning (i.e., modeling symmetry, anti-symmetry and inversion). Experimental results demonstrate that our method achieves state-of-the-art performance on four well-established knowledge graph completion benchmarks.

arXiv commentAccepted by NeurIPS 2019

References in corpus (6)

• A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Compositional Vector Space Models for Knowledge Base Completion
• Quaternion Recurrent Neural Networks
• Complex and Holographic Embeddings of Knowledge Graphs: A Comparison
• Knowledge Graph Embedding with Entity Neighbors and Deep Memory Network

Cited by in corpus (46)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure
• Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework
• Knowledge Graph Reasoning with Relational Digraph
• IMF: Interactive Multimodal Fusion Model for Link Prediction
• A Review of Knowledge Graph Completion
• Knowledge Graph informed Fake News Classification via Heterogeneous Representation Ensembles
• A Survey of Orthogonal Moments for Image Representation: Theory, Implementation, and Evaluation
• Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs
• Trans4E: Link Prediction on Scholarly Knowledge Graphs
• Temporal Knowledge Graph Embedding Model based on Additive Time Series Decomposition
• Multi-hop Attention Graph Neural Network
• Link Prediction with Attention Applied on Multiple Knowledge Graph Embedding Models
• Geometric Algebra based Embeddings for Static and Temporal Knowledge Graph Completion
• Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion
• PairRE: Knowledge Graph Embeddings via Paired Relation Vectors
• r-GAT: Relational Graph Attention Network for Multi-Relational Graphs
• Lightweight and Efficient Neural Natural Language Processing with Quaternion Networks
• MöbiusE: Knowledge Graph Embedding on Möbius Ring
• Learning Representations of Bi-level Knowledge Graphs for Reasoning beyond Link Prediction
• TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation
• Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding
• Towards Learning Instantiated Logical Rules from Knowledge Graphs
• AutoSF: Searching Scoring Functions for Knowledge Graph Embedding
• KGBoost: A Classification-based Knowledge Base Completion Method with Negative Sampling
• Relational Message Passing for Knowledge Graph Completion
• Quaternion Graph Neural Networks
• Group Representation Theory for Knowledge Graph Embedding
• An Adversarial Transfer Network for Knowledge Representation Learning
• Fully Hyperbolic Rotation for Knowledge Graph Embedding
• Out-of-Sample Representation Learning for Multi-Relational Graphs
• Type-augmented Relation Prediction in Knowledge Graphs
• Multi-Partition Embedding Interaction with Block Term Format for Knowledge Graph Completion
• Highly Efficient Knowledge Graph Embedding Learning with Orthogonal Procrustes Analysis
• Convolutional Hypercomplex Embeddings for Link Prediction
• Augmenting the User-Item Graph with Textual Similarity Models
• Combining Rules and Embeddings via Neuro-Symbolic AI for Knowledge Base Completion
• Knowledge Embedding Based Graph Convolutional Network
• Knowledge Graph Embeddings in Geometric Algebras
• A Literature Review of Recent Graph Embedding Techniques for Biomedical Data
• EM-RBR: a reinforced framework for knowledge graph completion from reasoning perspective
• RatE: Relation-Adaptive Translating Embedding for Knowledge Graph Completion
• HittER: Hierarchical Transformers for Knowledge Graph Embeddings
• Knowledge Sheaves: A Sheaf-Theoretic Framework for Knowledge Graph Embedding
• Quaternion-Based Graph Convolution Network for Recommendation
• Hyperbolic Geometry is Not Necessary: Lightweight Euclidean-Based Models for Low-Dimensional Knowledge Graph Embeddings