{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/109620"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/109620","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Belief propagation on factor graph neural networks","abstract":"Probabilistic graphical models are a statistical framework for conditionally dependent random variables with dependencies represented by graphs. A traditional method to perform inference over these random variables is Belief Propagation. Belief Propagation can be used to compute an exact solution for non-loopy factor graphs. However, when applied to loopy factor graphs, it only estimates marginal probabilities approximately. In this thesis, we propose a Graph Neural Networks (GNN) approach for belief propagation based on message passing mechanisms. In the proposed approach, representations and other functions are learned by the GNN. We apply this approach to the inference of loopy factor graphs. Furthermore, we show that learned representations and functions can also be generalized to factor graphs with different sizes and structures. The results show that our proposal has promising performance compared to the state of the art.","abstract_html":"Probabilistic graphical models are a statistical framework for conditionally dependent random variables with dependencies represented by graphs. A traditional method to perform inference over these random variables is Belief Propagation. Belief Propagation can be used to compute an exact solution for non-loopy factor graphs. However, when applied to loopy factor graphs, it only estimates marginal probabilities approximately. In this thesis, we propose a Graph Neural Networks (GNN) approach for belief propagation based on message passing mechanisms. In the proposed approach, representations and other functions are learned by the GNN. We apply this approach to the inference of loopy factor graphs. Furthermore, we show that learned representations and functions can also be generalized to factor graphs with different sizes and structures. The results show that our proposal has promising performance compared to the state of the art.","abstract_has_math":false,"creators":["Yin, Jialong"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Mechanical Engineering","degree_department":null,"school":null,"contributors":["Koyejo, Sanmi"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021-03-05T21:47:27Z","date_published":"2021-03-05T21:47:27Z","updated_at":"2026-07-22T22:24:50Z","subjects":["Belief Propagation","Graph Neural Networks"],"languages":["en"],"rights":["Copyright 2020 Jialong Yin"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/109620","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Koyejo, Sanmi"]},{"key":"dc:creator","label":"Author","values":["Yin, Jialong"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2021-03-05T21:47:27Z","2023-03-05T21:47:41Z","2020-12-18","2020-12"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Mechanical Engineering"]},{"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":["Belief Propagation","Graph Neural Networks"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2020 Jialong Yin"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/109620"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Probabilistic graphical models are a statistical framework for conditionally dependent random variables with dependencies represented by graphs. A traditional method to perform inference over these random variables is Belief Propagation. Belief Propagation can be used to compute an exact solution for non-loopy factor graphs. However, when applied to loopy factor graphs, it only estimates marginal probabilities approximately. In this thesis, we propose a Graph Neural Networks (GNN) approach for belief propagation based on message passing mechanisms. In the proposed approach, representations and other functions are learned by the GNN. We apply this approach to the inference of loopy factor graphs. Furthermore, we show that learned representations and functions can also be generalized to factor graphs with different sizes and structures. The results show that our proposal has promising performance compared to the state of the art.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2022-12-01","The student, Jialong Yin, accepted the attached license on 2020-12-02 at 05:34.","The student, Jialong Yin, submitted this Thesis for approval on 2020-12-02 at 05:42.","This Thesis was approved for publication on 2020-12-18 at 10:05.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16027 on 2021-03-04 at 16:33:13","Made available in DSpace on 2021-03-05T21:47:27Z (GMT). No. of bitstreams: 2 YIN-THESIS-2020.pdf: 2934723 bytes, checksum: 3fcc198870b1e25ebcf55be9c0153116 (MD5) LICENSE.txt: 4208 bytes, checksum: a5a60040618e2d8c8f31906b777f2752 (MD5) Previous issue date: 2020-12-18","Embargo set by: Seth Robbins for item 117326 Lift date: 2023-03-05T21:47:41Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Belief propagation on factor graph neural networks"]}]}],"canonical_facts":{"dc:contributor":["Koyejo, Sanmi"],"dc:creator":["Yin, Jialong"],"dc:date":["2021-03-05T21:47:27Z","2023-03-05T21:47:41Z","2020-12-18","2020-12"],"dc:description":["Probabilistic graphical models are a statistical framework for conditionally dependent random variables with dependencies represented by graphs. A traditional method to perform inference over these random variables is Belief Propagation. Belief Propagation can be used to compute an exact solution for non-loopy factor graphs. However, when applied to loopy factor graphs, it only estimates marginal probabilities approximately. In this thesis, we propose a Graph Neural Networks (GNN) approach for belief propagation based on message passing mechanisms. In the proposed approach, representations and other functions are learned by the GNN. We apply this approach to the inference of loopy factor graphs. Furthermore, we show that learned representations and functions can also be generalized to factor graphs with different sizes and structures. The results show that our proposal has promising performance compared to the state of the art.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2022-12-01","The student, Jialong Yin, accepted the attached license on 2020-12-02 at 05:34.","The student, Jialong Yin, submitted this Thesis for approval on 2020-12-02 at 05:42.","This Thesis was approved for publication on 2020-12-18 at 10:05.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16027 on 2021-03-04 at 16:33:13","Made available in DSpace on 2021-03-05T21:47:27Z (GMT). No. of bitstreams: 2 YIN-THESIS-2020.pdf: 2934723 bytes, checksum: 3fcc198870b1e25ebcf55be9c0153116 (MD5) LICENSE.txt: 4208 bytes, checksum: a5a60040618e2d8c8f31906b777f2752 (MD5) Previous issue date: 2020-12-18","Embargo set by: Seth Robbins for item 117326 Lift date: 2023-03-05T21:47:41Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/109620"],"dc:language":["en"],"dc:rights":["Copyright 2020 Jialong Yin"],"dc:subject":["Belief Propagation","Graph Neural Networks"],"dc:title":["Belief propagation on factor graph neural networks"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Mechanical Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:50Z"}