Relation Embedding with Dihedral Group in Knowledge Graph

Abstract

Link prediction is critical for the application of incomplete knowledge graph (KG) in the downstream tasks. As a family of effective approaches for link predictions, embedding methods try to learn low-rank representations for both entities and relations such that the bilinear form defined therein is a well-behaved scoring function. Despite of their successful performances, existing bilinear forms overlook the modeling of relation compositions, resulting in lacks of interpretability for reasoning on KG. To fulfill this gap, we propose a new model called DihEdral, named after dihedral symmetry group. This new model learns knowledge graph embeddings that can capture relation compositions by nature. Furthermore, our approach models the relation embeddings parametrized by discrete values, thereby decrease the solution space drastically. Our experiments show that DihEdral is able to capture all desired properties such as (skew-) symmetry, inversion and (non-) Abelian composition, and outperforms existing bilinear form based approach and is comparable to or better than deep learning models such as ConvE.

arXiv commentACL 2019

References in corpus (9)

• Categorical Reparameterization with Gumbel-Softmax
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• Complex Embeddings for Simple Link Prediction
• Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
• SimplE Embedding for Link Prediction in Knowledge Graphs
• Analogical Inference for Multi-Relational Embeddings
• ProjE: Embedding Projection for Knowledge Graph Completion
• Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs
• Modeling Relational Data with Graph Convolutional Networks

Cited by in corpus (9)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Review
• NagE: Non-Abelian Group Embedding for Knowledge Graphs
• Generalized Relation Learning with Semantic Correlation Awareness for Link Prediction
• Knowledge Graph Embedding with Atrous Convolution and Residual Learning
• Dynamic Relation Repairing for Knowledge Enhancement
• Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
• SEEK: Segmented Embedding of Knowledge Graphs
• Hyperbolic Geometry is Not Necessary: Lightweight Euclidean-Based Models for Low-Dimensional Knowledge Graph Embeddings