Knowledge Graph Fact Prediction via Knowledge-Enriched Tensor Factorization
Preprint
Abstract
We present a family of novel methods for embedding knowledge graphs into real-valued tensors. These tensor-based embeddings capture the ordered relations that are typical in the knowledge graphs represented by semantic web languages like RDF. Unlike many previous models, our methods can easily use prior background knowledge provided by users or extracted automatically from existing knowledge graphs. In addition to providing more robust methods for knowledge graph embedding, we provide a provably-convergent, linear tensor factorization algorithm. We demonstrate the efficacy of our models for the task of predicting new facts across eight different knowledge graphs, achieving between 5% and 50% relative improvement over existing state-of-the-art knowledge graph embedding techniques. Our empirical evaluation shows that all of the tensor decomposition models perform well when the average degree of an entity in a graph is high, with constraint-based models doing better on graphs with a small number of highly similar relations and regularization-based models dominating for graphs with relations of varying degrees of similarity.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Leveraging the schema in latent factor models for knowledge graph completion2016
- A Review of Relational Machine Learning for Knowledge GraphsProceedings of the IEEE, 2015
- KnowLife: a versatile approach for constructing a large knowledge graph for biomedical sciencesBMC Bioinformatics, 2015
- Knowledge Graph Embedding by Translating on HyperplanesProceedings of the AAAI Conference on Artificial Intelligence, 2014
- A semantic matching energy function for learning with multi-relational dataMachine Learning, 2013
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Tensor Factorization for Multi-relational Learning2013
- DBpedia: A Nucleus for a Web of Open Data2007
- PARAFAC. Tutorial and applicationsChemometrics and Intelligent Laboratory Systems, 1997
- PARAFAC: Parallel factor analysisComputational Statistics & Data Analysis, 1994