{"id":{"repo_id":"uic","oai_identifier":"oai:figshare.com:article/31451065"},"canonical_url":"https://search.dev.ndltd.org/etd/uic/oai:figshare.com:article/31451065","repository":{"repo_id":"uic","name":"University of Illinois - Chicago","base_url":"https://api.figshare.com/v2/oai"},"display":{"title":"Generative Models Driven Graph Outlier Detection","abstract":"Graph data are pervasive across various domains, including social networks, biological networks, and communication systems. The detection of outliers in graph data—substructures that significantly deviate from the norm—is crucial for uncovering fraudulent activities, network vulnerabilities, and novel patterns. However, traditional outlier detection techniques often fall short of effectively modeling the complex non-Euclidean graph data. Recently, generative models have exhibited extraordinary performance on image and language data, but their capabilities in graph outlier detection remain largely underexplored. In this dissertation, I systematically investigate the capabilities of generative models in the context of graph outlier detection, including four published works and one ongoing work. Specifically, first two works introduce a comprehensive graph outlier detection library and a benchmark on existing graph outlier detection algorithms. The third work presents a diffusion model–based data augmentation for addressing class imbalance in graph outlier detection. The fourth work explores scalable global spatiotemporal attention in graph Transformers for graph outlier detection. The last work focuses on the fake news detection capabilities of large language models and constructs a large-scale real-world text-attributed graph dataset for graph outlier detection.","abstract_html":"Graph data are pervasive across various domains, including social networks, biological networks, and communication systems. The detection of outliers in graph data—substructures that significantly deviate from the norm—is crucial for uncovering fraudulent activities, network vulnerabilities, and novel patterns. However, traditional outlier detection techniques often fall short of effectively modeling the complex non-Euclidean graph data. Recently, generative models have exhibited extraordinary performance on image and language data, but their capabilities in graph outlier detection remain largely underexplored. In this dissertation, I systematically investigate the capabilities of generative models in the context of graph outlier detection, including four published works and one ongoing work. Specifically, first two works introduce a comprehensive graph outlier detection library and a benchmark on existing graph outlier detection algorithms. The third work presents a diffusion model–based data augmentation for addressing class imbalance in graph outlier detection. The fourth work explores scalable global spatiotemporal attention in graph Transformers for graph outlier detection. The last work focuses on the fake news detection capabilities of large language models and constructs a large-scale real-world text-attributed graph dataset for graph outlier detection.","abstract_has_math":false,"creators":["Kay Zekuan Liu (23291320)"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-12-01T00:00:00Z","date_published":"2025-12-01T00:00:00Z","updated_at":"2026-07-27T21:34:21Z","subjects":["Computer Science"],"languages":[],"rights":["In Copyright"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.25417/uic.31451065.v1","outbound_label":"DOI","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Kay Zekuan Liu (23291320)"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-12-01T00:00:00Z"]},{"key":"dc:relation","label":"Dc Relation","values":["https://figshare.com/articles/thesis/Generative_Models_Driven_Graph_Outlier_Detection/31451065"]},{"key":"dc:type","label":"Dc Type","values":["Text","Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["10.25417/uic.31451065.v1"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Graph data are pervasive across various domains, including social networks, biological networks, and communication systems. The detection of outliers in graph data—substructures that significantly deviate from the norm—is crucial for uncovering fraudulent activities, network vulnerabilities, and novel patterns. However, traditional outlier detection techniques often fall short of effectively modeling the complex non-Euclidean graph data. Recently, generative models have exhibited extraordinary performance on image and language data, but their capabilities in graph outlier detection remain largely underexplored. In this dissertation, I systematically investigate the capabilities of generative models in the context of graph outlier detection, including four published works and one ongoing work. Specifically, first two works introduce a comprehensive graph outlier detection library and a benchmark on existing graph outlier detection algorithms. The third work presents a diffusion model–based data augmentation for addressing class imbalance in graph outlier detection. The fourth work explores scalable global spatiotemporal attention in graph Transformers for graph outlier detection. The last work focuses on the fake news detection capabilities of large language models and constructs a large-scale real-world text-attributed graph dataset for graph outlier detection."]},{"key":"dc:title","label":"Title","values":["Generative Models Driven Graph Outlier Detection"]}]}],"canonical_facts":{"dc:creator":["Kay Zekuan Liu (23291320)"],"dc:date":["2025-12-01T00:00:00Z"],"dc:description":["Graph data are pervasive across various domains, including social networks, biological networks, and communication systems. The detection of outliers in graph data—substructures that significantly deviate from the norm—is crucial for uncovering fraudulent activities, network vulnerabilities, and novel patterns. However, traditional outlier detection techniques often fall short of effectively modeling the complex non-Euclidean graph data. Recently, generative models have exhibited extraordinary performance on image and language data, but their capabilities in graph outlier detection remain largely underexplored. In this dissertation, I systematically investigate the capabilities of generative models in the context of graph outlier detection, including four published works and one ongoing work. Specifically, first two works introduce a comprehensive graph outlier detection library and a benchmark on existing graph outlier detection algorithms. The third work presents a diffusion model–based data augmentation for addressing class imbalance in graph outlier detection. The fourth work explores scalable global spatiotemporal attention in graph Transformers for graph outlier detection. The last work focuses on the fake news detection capabilities of large language models and constructs a large-scale real-world text-attributed graph dataset for graph outlier detection."],"dc:identifier":["10.25417/uic.31451065.v1"],"dc:relation":["https://figshare.com/articles/thesis/Generative_Models_Driven_Graph_Outlier_Detection/31451065"],"dc:rights":["In Copyright"],"dc:subject":["Computer Science"],"dc:title":["Generative Models Driven Graph Outlier Detection"],"dc:type":["Text","Thesis"]},"updated_at":"2026-07-27T21:34:21Z"}