Dissertation/Thesis Abstract

Improving Knowledge Graph Quality with Network Representation Learning
by Shi, Baoxu, Ph.D., University of Notre Dame, 2018, 108; 13836462
Abstract (Summary)

Knowledge graphs serve as an essential source for many tasks in data mining, artificial intelligence, and interdisciplinary challenges such as entity disambiguation, fact checking, and computational journalism. However, real-world knowledge graphs are far from perfect, so it remains a crucial task to improve the quality and completeness of these essential tools.

In this work, I present a representation learning-based approach to improve the quality of knowledge graphs through a process called Knowledge Graph Completion. This process finds missing connections among entities in the graph. I also propose a relaxed version of the knowledge graph completion task called Open-world Knowledge Graph Completion to complete and extend knowledge graphs with unobserved entities. Extensive evaluations on several data sets with different sizes shows the effectiveness of proposed methods for knowledge graph completion. Further experiments also demonstrate that these models can also solve tasks beyond Knowledge Graph Completion, such as classification, clustering, and recommendation tasks based on the representations learned from the knowledge graphs.

Indexing (document details)
School: University of Notre Dame
Department: Computer Science and Engineering
School Location: United States -- Indiana
Source: DAI-B 80/06(E), Dissertation Abstracts International
Subjects: Computer science
Keywords: Heterogeneous information network, Knowledge graph, Knowledge graph completion, Network representation learning
Publication Number: 13836462
ISBN: 978-0-438-83648-8
Copyright © 2020 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy