Complex Embeddings for Simple Link Prediction
Théo Trouillon, Johannes Welbl, Sebastian Riedel et al. · arXiv (Cornell University) · 2016
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.
Cited by 1,069 works. doi:10.48550/arxiv.1606.06357 Open-access PDF
Authors
References
- Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
- Matrix Factorization Techniques for Recommender Systems
- Freebase
- DBpedia: A Nucleus for a Web of Open Data
- Translating Embeddings for Modeling Multi-relational Data
- Reasoning With Neural Tensor Networks for Knowledge Base Completion
- Sur les matrices hypohermitiennes et sur les matrices unitaires
- A Three-Way Model for Collective Learning on Multi-Relational Data
- Embedding Entities and Relations for Learning and Inference in Knowledge Bases
- A Review of Relational Machine Learning for Knowledge Graphs