header

Knowledge Graph Fact Prediction Via Knowledge-Enriched Tensor Factorization

29 Pages Posted: 8 Feb 2019 First Look: Accepted

See all articles by Ankur Padia

Ankur Padia

University of Maryland, Baltimore County (UMBC)

Konstantinos Kalpakis

University of Maryland, Baltimore County (UMBC)

Francis Ferraro

University of Maryland, Baltimore County (UMBC)

Tim Finin

University of Maryland, Baltimore County (UMBC)

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: knowledge graph, knowledge graph embedding, tensor decomposition, tensor factorization, representation learning, fact prediction

Suggested Citation

Padia, Ankur and Kalpakis, Konstantinos and Ferraro, Francis and Finin, Tim, Knowledge Graph Fact Prediction Via Knowledge-Enriched Tensor Factorization (February 8, 2019). Available at SSRN: https://ssrn.com/abstract=3331039 or http://dx.doi.org/10.2139/ssrn.3331039

Ankur Padia

University of Maryland, Baltimore County (UMBC) ( email )

1000 Hilltop Circle
Baltimore, MD 21250
United States

Konstantinos Kalpakis

University of Maryland, Baltimore County (UMBC) ( email )

1000 Hilltop Circle
Baltimore, MD 21250
United States

Francis Ferraro

University of Maryland, Baltimore County (UMBC) ( email )

1000 Hilltop Circle
Baltimore, MD 21250
United States

Tim Finin (Contact Author)

University of Maryland, Baltimore County (UMBC) ( email )

1000 Hilltop Circle
Baltimore, MD 21250
United States

Register to save articles to
your library

Register

Paper statistics

Abstract Views
358
Downloads
46