No Cover Image

E-Thesis 301 views 137 downloads

Deep Learning on Graphs: Directed Graphs, Edge Structures and Graph Estimation / MICHAEL KENNING

Swansea University Author: MICHAEL KENNING

  • 2023_Kenning_MP.final.65374.pdf

    PDF | E-Thesis – open access

    Copyright: The Author, Michael P. Kenning, 2023. Distributed under the terms of a Creative Commons Attribution 4.0 International License (CC BY 4.0).

    Download (8.58MB)

DOI (Published version): 10.23889/SUthesis.65374

Abstract

In the last decade and a half, machine learning has been refounded on a class of techniques called deep learning. The earliest, most prominent techniques of deep learning were restricted in their application to regularly structured domains. A new set of techniques, broadly referred to as geometric d...

Full description

Published: Swansea, Wales, UK 2023
Institution: Swansea University
Degree level: Doctoral
Degree name: Ph.D
Supervisor: Xie, Xianghua.
URI: https://cronfa.swan.ac.uk/Record/cronfa65374
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2023-12-22T10:28:45Z
last_indexed 2023-12-22T10:28:45Z
id cronfa65374
recordtype RisThesis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>65374</id><entry>2023-12-22</entry><title>Deep Learning on Graphs: Directed Graphs, Edge Structures and Graph Estimation</title><swanseaauthors><author><sid>8ff473065824b311037bb11a4ec08c36</sid><firstname>MICHAEL</firstname><surname>KENNING</surname><name>MICHAEL KENNING</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-12-22</date><abstract>In the last decade and a half, machine learning has been refounded on a class of techniques called deep learning. The earliest, most prominent techniques of deep learning were restricted in their application to regularly structured domains. A new set of techniques, broadly referred to as geometric deep learning, extends the application of deep learning approaches to irregular domains, in particular the use of the graph. A graph is an effective means of representing irregular relations between discretely sampled points; its use has its attendant research challenges that has brought about a flourishing field of research. In this work we investigate three of those challenges, namely learning on directed graphs, one of the many variants of the graph; learning on the edge-structure of graphs; and graph estimation, i.e. the estimation of graph structure from the data itself. In the first chapter of our work, we consider the challenge of learning on the edge structure of a graph in application to a datacentre and present a convolution technique for the edge-structure of a directed graph representing a datacentre. In the second chapter of our work, we present a strategy to estimate two complementary graphs, the long-term or static graph and short-term or dynamic graph from combinations of temporal, cyclical data. Additionally, we propose an attention-based convolution for directed graphs that factorises neighbourhood signals into in- and out-flows. In the third and final chapter of our work, we draw on the work of the previous two chapters and design a graph estimation strategy to learn the complementary structures of molecular graphs. For this purpose, we define a new kind of graph for the estimation, which we call the graph complement, and use it in predicting molecular properties by incorporating intramolecular forces not present in the original graph. The structure thus learned is used to propagate vertex and edge signals on a directed graph. The work is concluded with a reflection on the contributions of the thesis and prospective areas of research in the field of graph deep learning.</abstract><type>E-Thesis</type><journal/><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher/><placeOfPublication>Swansea, Wales, UK</placeOfPublication><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords>Deep learning, graph deep learning, directed graph, edge learning, graph estimation</keywords><publishedDay>28</publishedDay><publishedMonth>11</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-11-28</publishedDate><doi>10.23889/SUthesis.65374</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><supervisor>Xie, Xianghua.</supervisor><degreelevel>Doctoral</degreelevel><degreename>Ph.D</degreename><degreesponsorsfunders>Swansea University Research Excellence Scholarship</degreesponsorsfunders><apcterm/><funders>Swansea University Research Excellence Scholarship</funders><projectreference/><lastEdited>2023-12-22T10:32:13.5999976</lastEdited><Created>2023-12-22T10:23:04.9310802</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>MICHAEL</firstname><surname>KENNING</surname><order>1</order></author></authors><documents><document><filename>65374__29317__fa8d66526d174cbe8380be02bfc00fb9.pdf</filename><originalFilename>2023_Kenning_MP.final.65374.pdf</originalFilename><uploaded>2023-12-22T10:28:13.6250959</uploaded><type>Output</type><contentLength>8996858</contentLength><contentType>application/pdf</contentType><version>E-Thesis – open access</version><cronfaStatus>true</cronfaStatus><documentNotes>Copyright: The Author, Michael P. Kenning, 2023. Distributed under the terms of a Creative Commons Attribution 4.0 International License (CC BY 4.0).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 65374 2023-12-22 Deep Learning on Graphs: Directed Graphs, Edge Structures and Graph Estimation 8ff473065824b311037bb11a4ec08c36 MICHAEL KENNING MICHAEL KENNING true false 2023-12-22 In the last decade and a half, machine learning has been refounded on a class of techniques called deep learning. The earliest, most prominent techniques of deep learning were restricted in their application to regularly structured domains. A new set of techniques, broadly referred to as geometric deep learning, extends the application of deep learning approaches to irregular domains, in particular the use of the graph. A graph is an effective means of representing irregular relations between discretely sampled points; its use has its attendant research challenges that has brought about a flourishing field of research. In this work we investigate three of those challenges, namely learning on directed graphs, one of the many variants of the graph; learning on the edge-structure of graphs; and graph estimation, i.e. the estimation of graph structure from the data itself. In the first chapter of our work, we consider the challenge of learning on the edge structure of a graph in application to a datacentre and present a convolution technique for the edge-structure of a directed graph representing a datacentre. In the second chapter of our work, we present a strategy to estimate two complementary graphs, the long-term or static graph and short-term or dynamic graph from combinations of temporal, cyclical data. Additionally, we propose an attention-based convolution for directed graphs that factorises neighbourhood signals into in- and out-flows. In the third and final chapter of our work, we draw on the work of the previous two chapters and design a graph estimation strategy to learn the complementary structures of molecular graphs. For this purpose, we define a new kind of graph for the estimation, which we call the graph complement, and use it in predicting molecular properties by incorporating intramolecular forces not present in the original graph. The structure thus learned is used to propagate vertex and edge signals on a directed graph. The work is concluded with a reflection on the contributions of the thesis and prospective areas of research in the field of graph deep learning. E-Thesis Swansea, Wales, UK Deep learning, graph deep learning, directed graph, edge learning, graph estimation 28 11 2023 2023-11-28 10.23889/SUthesis.65374 COLLEGE NANME COLLEGE CODE Swansea University Xie, Xianghua. Doctoral Ph.D Swansea University Research Excellence Scholarship Swansea University Research Excellence Scholarship 2023-12-22T10:32:13.5999976 2023-12-22T10:23:04.9310802 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science MICHAEL KENNING 1 65374__29317__fa8d66526d174cbe8380be02bfc00fb9.pdf 2023_Kenning_MP.final.65374.pdf 2023-12-22T10:28:13.6250959 Output 8996858 application/pdf E-Thesis – open access true Copyright: The Author, Michael P. Kenning, 2023. Distributed under the terms of a Creative Commons Attribution 4.0 International License (CC BY 4.0). true eng https://creativecommons.org/licenses/by/4.0/
title Deep Learning on Graphs: Directed Graphs, Edge Structures and Graph Estimation
spellingShingle Deep Learning on Graphs: Directed Graphs, Edge Structures and Graph Estimation
MICHAEL KENNING
title_short Deep Learning on Graphs: Directed Graphs, Edge Structures and Graph Estimation
title_full Deep Learning on Graphs: Directed Graphs, Edge Structures and Graph Estimation
title_fullStr Deep Learning on Graphs: Directed Graphs, Edge Structures and Graph Estimation
title_full_unstemmed Deep Learning on Graphs: Directed Graphs, Edge Structures and Graph Estimation
title_sort Deep Learning on Graphs: Directed Graphs, Edge Structures and Graph Estimation
author_id_str_mv 8ff473065824b311037bb11a4ec08c36
author_id_fullname_str_mv 8ff473065824b311037bb11a4ec08c36_***_MICHAEL KENNING
author MICHAEL KENNING
author2 MICHAEL KENNING
format E-Thesis
publishDate 2023
institution Swansea University
doi_str_mv 10.23889/SUthesis.65374
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 1
active_str 0
description In the last decade and a half, machine learning has been refounded on a class of techniques called deep learning. The earliest, most prominent techniques of deep learning were restricted in their application to regularly structured domains. A new set of techniques, broadly referred to as geometric deep learning, extends the application of deep learning approaches to irregular domains, in particular the use of the graph. A graph is an effective means of representing irregular relations between discretely sampled points; its use has its attendant research challenges that has brought about a flourishing field of research. In this work we investigate three of those challenges, namely learning on directed graphs, one of the many variants of the graph; learning on the edge-structure of graphs; and graph estimation, i.e. the estimation of graph structure from the data itself. In the first chapter of our work, we consider the challenge of learning on the edge structure of a graph in application to a datacentre and present a convolution technique for the edge-structure of a directed graph representing a datacentre. In the second chapter of our work, we present a strategy to estimate two complementary graphs, the long-term or static graph and short-term or dynamic graph from combinations of temporal, cyclical data. Additionally, we propose an attention-based convolution for directed graphs that factorises neighbourhood signals into in- and out-flows. In the third and final chapter of our work, we draw on the work of the previous two chapters and design a graph estimation strategy to learn the complementary structures of molecular graphs. For this purpose, we define a new kind of graph for the estimation, which we call the graph complement, and use it in predicting molecular properties by incorporating intramolecular forces not present in the original graph. The structure thus learned is used to propagate vertex and edge signals on a directed graph. The work is concluded with a reflection on the contributions of the thesis and prospective areas of research in the field of graph deep learning.
published_date 2023-11-28T10:32:14Z
_version_ 1785977776058138624
score 11.037581

Similar Items