{"id":{"repo_id":"baylor","oai_identifier":"oai:baylor-ir.tdl.org:2104/14637"},"canonical_url":"https://search.dev.ndltd.org/etd/baylor/oai:baylor-ir.tdl.org:2104/14637","repository":{"repo_id":"baylor","name":"Baylor University","base_url":"https://baylor-ir.tdl.org/server/oai/request"},"display":{"title":"Robust graph representation learning with structure-aware attention and self-supervised contrastive frameworks.","abstract":"Graph-structured data is pervasive across domains such as social networks, biological systems, and information networks, yet effectively learning from such data remains a fundamental challenge in machine learning. My dissertation focuses on developing novel graph representation learning methods that enhance predictive performance, robustness, and interpretability for node and graph classification tasks. Specifically, I investigate attention-based Graph Neural Networks (GNNs) and their variants, designing structure-aware and contrastive learning strategies to capture both local and global dependencies in graphs. Through extensive experiments on benchmark and real-world datasets, I demonstrate how these methods improve accuracy, scalability, and fairness compared to traditional GNN models. In addition, I explore applications in document classification, social network analysis, and ethical AI, highlighting how integrating domain knowledge and attention mechanisms can support more reliable and interpretable predictions. This work advances the understanding of graph representation learning and provides practical methodologies for deploying GNNs in diverse, real-world scenarios, bridging the gap between theoretical innovation and applied machine learning.","abstract_html":"Graph-structured data is pervasive across domains such as social networks, biological systems, and information networks, yet effectively learning from such data remains a fundamental challenge in machine learning. My dissertation focuses on developing novel graph representation learning methods that enhance predictive performance, robustness, and interpretability for node and graph classification tasks. Specifically, I investigate attention-based Graph Neural Networks (GNNs) and their variants, designing structure-aware and contrastive learning strategies to capture both local and global dependencies in graphs. Through extensive experiments on benchmark and real-world datasets, I demonstrate how these methods improve accuracy, scalability, and fairness compared to traditional GNN models. In addition, I explore applications in document classification, social network analysis, and ethical AI, highlighting how integrating domain knowledge and attention mechanisms can support more reliable and interpretable predictions. This work advances the understanding of graph representation learning and provides practical methodologies for deploying GNNs in diverse, real-world scenarios, bridging the gap between theoretical innovation and applied machine learning.","abstract_has_math":false,"creators":["Jui, Tonni Das, 1995-"],"institution":"Baylor University.","degree_name":"Ph.D.","degree_level":"Doctoral","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Benton, Mary Lauren."],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026-05","date_published":"2026-05","updated_at":"2026-07-24T01:07:49Z","subjects":["Graph machine learning.","Graph neural networks (GNNs)","Machine learning."],"languages":["en"],"rights":["Baylor University works are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. Contact libraryquestions@baylor.edu for inquiries about permission."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2104/14637","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Benton, Mary Lauren."]},{"key":"dc:creator","label":"Author","values":["Jui, Tonni Das, 1995-"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-04-08T13:58:59Z"]},{"key":"dc:date.issued","label":"Date","values":["2026-05"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Doctoral"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Baylor University."]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Graph machine learning.","Graph neural networks (GNNs)","Machine learning."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Baylor University works are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. Contact libraryquestions@baylor.edu for inquiries about permission."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/2104/14637"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Graph-structured data is pervasive across domains such as social networks, biological systems, and information networks, yet effectively learning from such data remains a fundamental challenge in machine learning. My dissertation focuses on developing novel graph representation learning methods that enhance predictive performance, robustness, and interpretability for node and graph classification tasks. Specifically, I investigate attention-based Graph Neural Networks (GNNs) and their variants, designing structure-aware and contrastive learning strategies to capture both local and global dependencies in graphs. Through extensive experiments on benchmark and real-world datasets, I demonstrate how these methods improve accuracy, scalability, and fairness compared to traditional GNN models. In addition, I explore applications in document classification, social network analysis, and ethical AI, highlighting how integrating domain knowledge and attention mechanisms can support more reliable and interpretable predictions. This work advances the understanding of graph representation learning and provides practical methodologies for deploying GNNs in diverse, real-world scenarios, bridging the gap between theoretical innovation and applied machine learning."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Robust graph representation learning with structure-aware attention and self-supervised contrastive frameworks."]}]}],"canonical_facts":{"dc:contributor.advisor":["Benton, Mary Lauren."],"dc:creator":["Jui, Tonni Das, 1995-"],"dc:date.accessioned":["2026-04-08T13:58:59Z"],"dc:date.issued":["2026-05"],"dc:description.abstract":["Graph-structured data is pervasive across domains such as social networks, biological systems, and information networks, yet effectively learning from such data remains a fundamental challenge in machine learning. My dissertation focuses on developing novel graph representation learning methods that enhance predictive performance, robustness, and interpretability for node and graph classification tasks. Specifically, I investigate attention-based Graph Neural Networks (GNNs) and their variants, designing structure-aware and contrastive learning strategies to capture both local and global dependencies in graphs. Through extensive experiments on benchmark and real-world datasets, I demonstrate how these methods improve accuracy, scalability, and fairness compared to traditional GNN models. In addition, I explore applications in document classification, social network analysis, and ethical AI, highlighting how integrating domain knowledge and attention mechanisms can support more reliable and interpretable predictions. This work advances the understanding of graph representation learning and provides practical methodologies for deploying GNNs in diverse, real-world scenarios, bridging the gap between theoretical innovation and applied machine learning."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/2104/14637"],"dc:language.iso":["en"],"dc:rights":["Baylor University works are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. Contact libraryquestions@baylor.edu for inquiries about permission."],"dc:subject":["Graph machine learning.","Graph neural networks (GNNs)","Machine learning."],"dc:title":["Robust graph representation learning with structure-aware attention and self-supervised contrastive frameworks."],"dc:type":["Thesis"],"thesis:degree_level":["Doctoral"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["Baylor University."]},"updated_at":"2026-07-24T01:07:49Z"}