Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form
D-Scholarship @ Pitt Banner and Links to Homepage

New Graph-based Representation Learning Algorithms

Zhang, Yanfu (2023) New Graph-based Representation Learning Algorithms. Doctoral Dissertation, University of Pittsburgh. (Unpublished)

[img]
Preview
 PDF
Download (4MB) | Preview

Abstract

In recent years, graph neural networks (GNN) have succeeded in many structural data analyses, including information retrieval, recommendation system, and social network analysis. Although the first-order graph convolutional networks are initially designed for single-view node-level representation learning, the graph-level analysis using GNNs applies according to recent studies, e.g., the shared structures can be learned from single-view graph data. The dissertation focuses on the efficient and robust graph-level representation learning using GNNs. Several effective methods are proposed to address the critical problems in graph representation learning, including over-smoothing, graph structural difference, and fast training. The application of graph representation learning on medical data is also studied, including new methods for single-view, multi-view, and unsupervised medical data analysis.

Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: University of Pittsburgh ETD
Status: Unpublished
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Zhang, Yanfuyaz91@pitt.edu
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Thesis AdvisorHuang, Henghenghuanghh@gmail.com
Committee MemberGao, Weiweigao@pitt.edu
Committee MemberZhan, Liangliang.zhan@pitt.edu
Committee MemberMao, Zhi-Hongzhm4@pitt.edu
Committee MemberChen, Weiwei.chen@pitt.edu
Date: 14 September 2023
Date Type: Publication
Defense Date: 27 June 2023
Approval Date: 14 September 2023
Submission Date: 21 July 2023
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Number of Pages: 141
Institution: University of Pittsburgh
Schools and Programs: Swanson School of Engineering > Electrical and Computer Engineering
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: machine learning, deep learning, graph neural neural networks
Date Deposited: 14 Sep 2023 13:43
Last Modified: 14 Sep 2023 13:43
URI: http://d-scholarship.pitt.edu/id/eprint/45125

Metrics

Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item