2026-09-18T19:36:33Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/102848 2023-07-11 col_2142_5131 col_2142_8888 com_2142_5130 com_2142_8887 com_2142_234

Oh, Sewoong Liu, Xiyang 2019-02-07T20:44:26Z 2019-02-07T20:44:26Z 2021-02-08T10:15:36Z 2018-12-10 2018-12 Graph matching or network alignment refers to the problem of matching two correlated graphs. This thesis presents a deep Q learning based method, which represents the matching process by a graph neural network. By breaking the symmetry, the parameterized graph neural network is able to capture a wide range of neighborhoods. Extensive experiments on various training and testing data have shown better performance, strong scalability and the ability to adapt to different domains. Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2020-12-01 The student, Xiyang Liu, accepted the attached license on 2018-12-07 at 14:38. The student, Xiyang Liu, submitted this Thesis for approval on 2018-12-07 at 14:45. This Thesis was approved for publication on 2018-12-10 at 08:10. DSpace SAF Submission Ingestion Package generated from Vireo submission #13256 on 2019-02-07 at 14:23:06 Made available in DSpace on 2019-02-07T20:44:26Z (GMT). No. of bitstreams: 2 LIU-THESIS-2018.pdf: 657272 bytes, checksum: c560b91fb966ccaa322367ec0cbcf154 (MD5) LICENSE.txt: 4207 bytes, checksum: d64a3f0c83a6f0dcf849a1a41d00b161 (MD5) Previous issue date: 2018-12-10 Embargo set by: Seth Robbins for item 109874 Lift date: 2021-02-07T20:44:35Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system U of I Only Restriction Lifted for Item 109874 on 2021-02-08T10:15:36Z. application/pdf http://hdl.handle.net/2142/102848 en Copyright 2018 Xiyang Liu Graph Neural Network, Graph Matching Graph matching by graph neural network text text Electrical & Computer Eng Electrical & Computer Engr University of Illinois at Urbana-Champaign Thesis M.S.