Knowledge Graph Inference using Tensor Embedding

Thumbnail Image

Files

1032.pdf (1.32 MB)

Links to Files

https://ebiquity.umbc.edu/paper/html/id/943/Knowledge-Graph-Inference-using-Tensor-Embedding

Permanent Link

http://hdl.handle.net/11603/21282

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection

Author/Creator

Author/Creator ORCID

Date

2020-09-12

Type of Work

conference paper and proceedings postprints
Text

Department

Program

Citation of Original Publication

Ankur Padia; Kalpakis, Kostantinos; Ferraro, Francis; Finin, Tim; Knowledge Graph Inference using Tensor Embedding; 17th International Conference on Principles of Knowledge Representation and Reasoning (2020); https://ebiquity.umbc.edu/paper/html/id/943/Knowledge-Graph-Inference-using-Tensor-Embedding

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.

Subjects

UMBC High Performance Computer Facility (HPCF)

Abstract

Axiom based inference provides a clear and consistent way of reasoning to add more information to a knowledge graph. However, constructing a set of axioms is expensive and requires domain expertise, time, and money. It is also difficult to reuse or adapt a set of axioms to a knowledge graph in a new domain or even in the same domain but using a slightly different representation approach. This work makes three main contributions, it (1) provides a family of representation learning algorithms and an extensive analysis on eight datasets; (2) yields better results than existing tensor and neural models; and (3) includes a provably convergent factorization algorithm.