"Large Scale Machine Learning over Knowledge Graphs" by Bedirhan Gergin

ORCID

https://orcid.org/0000-0002-9362-6461

Date of Award

Spring 2025

Language

English

Embargo Period

11-30-2025

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

College/School/Department

Department of Computer Science

Program

Computer Science

First Advisor

Charalampos Chelmis

Committee Members

Amir Masoumzadeh, Petko Bogdanov, Jeong-Hyon Hwang

Keywords

Knowledge Graphs, RDF, Distributed Computing, Big Data infrastructure, Ensemble Learning, Link Prediction

Subject Categories

Artificial Intelligence and Robotics | Computer Sciences | Data Science | Other Computer Sciences | Software Engineering | Systems Architecture | Theory and Algorithms

Abstract

Knowledge graphs (KGs) have become popular across various fields, providing convenient access to web-based knowledge while storing and formalizing domain-specific information. By analyzing KGs, patterns, connections, and dependencies can be identified across different data sources, enabling the inference of new knowledge from given facts. As the use of KGs expands, the size of modern KGs has grown significantly, making them impossible to process within the main memory of a single computer. Distributed computing offers a viable solution to this challenge by leveraging the combined capabilities of multiple servers within a cluster. This thesis explores how distributed computing can be effectively utilized to perform machine learning over large knowledge graphs, with a focus on facilitating scalable analytics and accelerating downstream tasks. Specifically, this thesis addresses three core challenges: (i) how to facilitate analytics over Knowledge Graphs in Apache Spark, (ii) how to compute KG embeddings at scale, and (iii) how to accelerate and enhance a representative downstream task.

License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Available for download on Sunday, November 30, 2025

Share

COinS