{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/120378"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/120378","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Generative gradual domain adaptation with optimal transport","abstract":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2025-05-01","abstract_html":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2025-05-01","abstract_has_math":false,"creators":["He, Yifei"],"institution":"University of Illinois at 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":2023,"date_issued":"2023-05","date_published":"2023-05","updated_at":"2026-07-22T22:24:57Z","subjects":["Domain Adaptation","Distribution Shift"],"languages":["en","eng"],"rights":["Copyright 2023 Yifei He"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/120378","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":["He, Yifei"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2023-05","2023-04-17"]},{"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 at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Domain Adaptation","Distribution Shift"]}]},{"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 2023 Yifei He"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/120378"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2025-05-01","The student, Yifei He, accepted the attached license on 2023-04-17 at 10:35.","The student, Yifei He, submitted this Thesis for approval on 2023-04-17 at 10:50.","This Thesis was approved for publication on 2023-04-17 at 15:53.","DSpace SAF Submission Ingestion Package generated from Vireo submission #19007 on 2023-09-01 at 17:13:34","Unsupervised domain adaptation (UDA) adapts a model from a labeled source domain to an unlabeled target domain in a one-off way. Though widely applied, UDA faces a great challenge whenever the distribution shift between the source and the target is large. Gradual domain adaptation (GDA) mitigates this limitation by using intermediate domains to gradually adapt from the source to the target domain. However, it remains an open problem on how to leverage this paradigm when the given intermediate domains are missing or scarce. To approach this practical challenge, we propose Generative Gradual DOmain Adaptation with Optimal Transport (GOAT), an algorithmic framework that can generate intermediate domains in a data-dependent way. More concretely, we first generate intermediate domains along the Wasserstein geodesic between two given consecutive domains in a feature space, and apply gradual self-training, a standard GDA algorithm, to adapt the source-trained classifier to the target along the sequence of intermediate domains. Empirically, we demonstrate that our GOAT framework can improve the performance of standard GDA when the given intermediate domains are scarce, significantly broadening the real-world application scenarios of GDA."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Generative gradual domain adaptation with optimal transport"]}]}],"canonical_facts":{"dc:contributor":["Zhao, Han"],"dc:creator":["He, Yifei"],"dc:date":["2023-05","2023-04-17"],"dc:description":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2025-05-01","The student, Yifei He, accepted the attached license on 2023-04-17 at 10:35.","The student, Yifei He, submitted this Thesis for approval on 2023-04-17 at 10:50.","This Thesis was approved for publication on 2023-04-17 at 15:53.","DSpace SAF Submission Ingestion Package generated from Vireo submission #19007 on 2023-09-01 at 17:13:34","Unsupervised domain adaptation (UDA) adapts a model from a labeled source domain to an unlabeled target domain in a one-off way. Though widely applied, UDA faces a great challenge whenever the distribution shift between the source and the target is large. Gradual domain adaptation (GDA) mitigates this limitation by using intermediate domains to gradually adapt from the source to the target domain. However, it remains an open problem on how to leverage this paradigm when the given intermediate domains are missing or scarce. To approach this practical challenge, we propose Generative Gradual DOmain Adaptation with Optimal Transport (GOAT), an algorithmic framework that can generate intermediate domains in a data-dependent way. More concretely, we first generate intermediate domains along the Wasserstein geodesic between two given consecutive domains in a feature space, and apply gradual self-training, a standard GDA algorithm, to adapt the source-trained classifier to the target along the sequence of intermediate domains. Empirically, we demonstrate that our GOAT framework can improve the performance of standard GDA when the given intermediate domains are scarce, significantly broadening the real-world application scenarios of GDA."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/120378"],"dc:language":["en","eng"],"dc:rights":["Copyright 2023 Yifei He"],"dc:subject":["Domain Adaptation","Distribution Shift"],"dc:title":["Generative gradual domain adaptation with 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 at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:57Z"}