{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/124326"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/124326","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Temporal hypergraph modeling via inter-geometrical learning","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms","abstract_has_math":false,"creators":["Agarwal, Shivam"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Han, Jiawei","Peng, Hao"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-05","date_published":"2024-05","updated_at":"2026-07-22T22:25:00Z","subjects":["Graph Neural Networks","Spatio-temporal Learning","Machine Learning"],"languages":["en","eng"],"rights":["Copyright 2024 Shivam Agarwal"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/124326","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Han, Jiawei","Peng, Hao"]},{"key":"dc:creator","label":"Author","values":["Agarwal, Shivam"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024-05","2024-04-26"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Graph Neural Networks","Spatio-temporal Learning","Machine Learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2024 Shivam Agarwal"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/124326"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms","The student, Shivam Agarwal, accepted the attached license on 2024-04-17 at 22:18.","The student, Shivam Agarwal, submitted this Thesis for approval on 2024-04-17 at 22:23.","This Thesis was approved for publication on 2024-04-26 at 15:32.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20472 on 2024-09-16 at 00:35:22","Hyperbolic geometry has advanced learning representations on graphs with inherently complex geometrical and hierarchical characteristics. However, most real world networks innately comprise of higher-order relations, dynamic behavior, and scale-free temporal characteristics with varying degrees of hyperbolicity. Combating these gaps, we propose THRONE, a temporal, inter-geometrical interaction learning-based hypergraph convolution method to capitalize on the complex, time-varying, higher-order relations and the varying hyperbolicity of network structures. Further, we enhance the hypergraph convolution by applying attention infused with hyperbolic distance information among node and hyperedge representations. THRONE incorporates hyperbolic temporal convolution layers to encode scale-free spatio-temporal information and dynamic time-evolving network structures. We extend THRONE to hypergraph-level tasks by introducing THRONE-Pool, a novel hyperbolic hypergraph pooling method to encode higher-order scale-free networks. Through a series of quantitative and exploratory analyses on ten node-level and six network-level tasks across static, spatio-temporal, and time-evolving dynamic hypergraphs, we demonstrate THRONE's practical applicability in comparison to competitive baselines. We dissect THRONE's performance contributions on a variety of benchmarks and applications spanning finance, health, traffic, wind energy, and citation networks through ablations to highlight the effectiveness of each component. Through THRONE, we take a step forward in devising a data, task, hyperbolicity and network agnostic method for learning representations."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Temporal hypergraph modeling via inter-geometrical learning"]}]}],"canonical_facts":{"dc:contributor":["Han, Jiawei","Peng, Hao"],"dc:creator":["Agarwal, Shivam"],"dc:date":["2024-05","2024-04-26"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms","The student, Shivam Agarwal, accepted the attached license on 2024-04-17 at 22:18.","The student, Shivam Agarwal, submitted this Thesis for approval on 2024-04-17 at 22:23.","This Thesis was approved for publication on 2024-04-26 at 15:32.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20472 on 2024-09-16 at 00:35:22","Hyperbolic geometry has advanced learning representations on graphs with inherently complex geometrical and hierarchical characteristics. However, most real world networks innately comprise of higher-order relations, dynamic behavior, and scale-free temporal characteristics with varying degrees of hyperbolicity. Combating these gaps, we propose THRONE, a temporal, inter-geometrical interaction learning-based hypergraph convolution method to capitalize on the complex, time-varying, higher-order relations and the varying hyperbolicity of network structures. Further, we enhance the hypergraph convolution by applying attention infused with hyperbolic distance information among node and hyperedge representations. THRONE incorporates hyperbolic temporal convolution layers to encode scale-free spatio-temporal information and dynamic time-evolving network structures. We extend THRONE to hypergraph-level tasks by introducing THRONE-Pool, a novel hyperbolic hypergraph pooling method to encode higher-order scale-free networks. Through a series of quantitative and exploratory analyses on ten node-level and six network-level tasks across static, spatio-temporal, and time-evolving dynamic hypergraphs, we demonstrate THRONE's practical applicability in comparison to competitive baselines. We dissect THRONE's performance contributions on a variety of benchmarks and applications spanning finance, health, traffic, wind energy, and citation networks through ablations to highlight the effectiveness of each component. Through THRONE, we take a step forward in devising a data, task, hyperbolicity and network agnostic method for learning representations."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/124326"],"dc:language":["en","eng"],"dc:rights":["Copyright 2024 Shivam Agarwal"],"dc:subject":["Graph Neural Networks","Spatio-temporal Learning","Machine Learning"],"dc:title":["Temporal hypergraph modeling via inter-geometrical learning"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:00Z"}