{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/129673"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/129673","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Learning structured representations by embedding class hierarchy with fast optimal transport","abstract":"Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-05-01","abstract_html":"Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-05-01","abstract_has_math":false,"creators":["Zeng, Siqi"],"institution":"University of Illinois Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Zhao, Han"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-04-21","date_published":"2025-04-21","updated_at":"2026-07-22T22:25:05Z","subjects":["hierarchical representation","representation learning","optimal transport"],"languages":["en","eng"],"rights":["Copyright 2025 Siqi Zeng"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/129673","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Zhao, Han"]},{"key":"dc:creator","label":"Author","values":["Zeng, Siqi"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-04-21","2025-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"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 Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["hierarchical representation","representation learning","optimal transport"]}]},{"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 2025 Siqi Zeng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/129673"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-05-01","The student, Siqi Zeng, accepted the attached license on 2025-04-21 at 16:12.","The student, Siqi Zeng, submitted this Thesis for approval on 2025-04-21 at 16:18.","This Thesis was approved for publication on 2025-04-21 at 16:47.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21684 on 2025-10-19 at 19:52:32","To embed structured knowledge within labels into feature representations, prior work (Zeng et al., 2022) proposed to use the Cophenetic Correlation Coefficient (CPCC) as a regularizer during supervised learning. This regularizer calculates pairwise Euclidean distances of class means and aligns them with the corresponding shortest path distances derived from the label hierarchy tree. However, class means may not be good representatives of the class conditional distributions, especially when they are multi-mode in nature. To address this limitation, under the CPCC framework, we propose to use the Earth Mover's Distance (EMD) to measure the pairwise distances among classes in the feature space. We show that our exact EMD method generalizes previous work, and recovers the existing algorithm when class-conditional distributions are Gaussian in the feature space. To further improve the computational efficiency of our method, we introduce the Optimal Transport-CPCC family by exploring four EMD approximation variants. Our most efficient OT-CPCC variant runs in linear time in the size of the dataset, while maintaining competitive performance across datasets and tasks. The code is available at https://github.com/uiuctml/OTCPCC."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Learning structured representations by embedding class hierarchy with fast optimal transport"]}]}],"canonical_facts":{"dc:contributor":["Zhao, Han"],"dc:creator":["Zeng, Siqi"],"dc:date":["2025-04-21","2025-05"],"dc:description":["Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-05-01","The student, Siqi Zeng, accepted the attached license on 2025-04-21 at 16:12.","The student, Siqi Zeng, submitted this Thesis for approval on 2025-04-21 at 16:18.","This Thesis was approved for publication on 2025-04-21 at 16:47.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21684 on 2025-10-19 at 19:52:32","To embed structured knowledge within labels into feature representations, prior work (Zeng et al., 2022) proposed to use the Cophenetic Correlation Coefficient (CPCC) as a regularizer during supervised learning. This regularizer calculates pairwise Euclidean distances of class means and aligns them with the corresponding shortest path distances derived from the label hierarchy tree. However, class means may not be good representatives of the class conditional distributions, especially when they are multi-mode in nature. To address this limitation, under the CPCC framework, we propose to use the Earth Mover's Distance (EMD) to measure the pairwise distances among classes in the feature space. We show that our exact EMD method generalizes previous work, and recovers the existing algorithm when class-conditional distributions are Gaussian in the feature space. To further improve the computational efficiency of our method, we introduce the Optimal Transport-CPCC family by exploring four EMD approximation variants. Our most efficient OT-CPCC variant runs in linear time in the size of the dataset, while maintaining competitive performance across datasets and tasks. The code is available at https://github.com/uiuctml/OTCPCC."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/129673"],"dc:language":["en","eng"],"dc:rights":["Copyright 2025 Siqi Zeng"],"dc:subject":["hierarchical representation","representation learning","optimal transport"],"dc:title":["Learning structured representations by embedding class hierarchy with fast optimal transport"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:05Z"}