Multi-relational Poincaré Graph Embeddings
arXiv:1905.09791
Abstract
Hyperbolic embeddings have recently gained attention in machine learning due to their ability to represent hierarchical data more accurately and succinctly than their Euclidean analogues. However, multi-relational knowledge graphs often exhibit multiple simultaneous hierarchies, which current hyperbolic models do not capture. To address this, we propose a model that embeds multi-relational graph data in the Poincaré ball model of hyperbolic space. Our Multi-Relational Poincaré model (MuRP) learns relation-specific parameters to transform entity embeddings by Möbius matrix-vector multiplication and Möbius addition. Experiments on the hierarchical WN18RR knowledge graph show that our Poincaré embeddings outperform their Euclidean counterpart and existing embedding methods on the link prediction task, particularly at lower dimensionality.
References in corpus (7)
- Distributed Representations of Words and Phrases and their Compositionality
- RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
- Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
- Poincaré GloVe: Hyperbolic Word Embeddings
- Riemannian Adaptive Optimization Methods
- M-Walk: Learning to Walk over Graphs using Monte Carlo Tree Search
- Analogies Explained: Towards Understanding Word Embeddings
Cited by in corpus (8)
- A Survey on Knowledge Graphs: Representation, Acquisition and Applications
- Machine Learning on Graphs: A Model and Comprehensive Taxonomy
- HyperKG: Hyperbolic Knowledge Graph Embeddings for Knowledge Base Completion
- Hyperbolic Deep Neural Networks: A Survey
- A Hyperbolic-to-Hyperbolic Graph Convolutional Network
- Billion-scale Pre-trained E-commerce Product Knowledge Graph Model
- Conformal retrofitting via Riemannian manifolds: distilling task-specific graphs into pretrained embeddings
- Hyperbolic Multiplex Network Embedding with Maps of Random Walk