{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/107976"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/107976","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Network motif prediction using generative models for graphs","abstract":"Graphs are commonly used to represent pairwise interactions between different entities in networks. Generative graph models create new graphs that mimic the properties of already existing graphs. Generative models are successful at retaining the pairwise interactions of the underlying networks but often fail to capture higher-order connectivity patterns between more than two entities. A network motif is one such pattern observed in various realworld networks. Different types of graphs contain different network motifs, an example of which are triangles that often arise in social and biological networks. Motifs model important functional properties of the graph. Hence, it is vital to capture these higher-order structures to simulate real-world networks accurately. This thesis introduces a motif-targeted graph generative model based on a generative adversarial network (GAN) architecture that generalizes and outperforms the current benchmark approach, NetGAN, at motif prediction. This model and its extension to hypergraphs are tested on real-world social and biological network data, and they are shown to be better at both capturing the underlying motif statistics in the networks as well as predicting missing motifs in incomplete networks.","abstract_html":"Graphs are commonly used to represent pairwise interactions between different entities in networks. Generative graph models create new graphs that mimic the properties of already existing graphs. Generative models are successful at retaining the pairwise interactions of the underlying networks but often fail to capture higher-order connectivity patterns between more than two entities. A network motif is one such pattern observed in various realworld networks. Different types of graphs contain different network motifs, an example of which are triangles that often arise in social and biological networks. Motifs model important functional properties of the graph. Hence, it is vital to capture these higher-order structures to simulate real-world networks accurately. This thesis introduces a motif-targeted graph generative model based on a generative adversarial network (GAN) architecture that generalizes and outperforms the current benchmark approach, NetGAN, at motif prediction. This model and its extension to hypergraphs are tested on real-world social and biological network data, and they are shown to be better at both capturing the underlying motif statistics in the networks as well as predicting missing motifs in incomplete networks.","abstract_has_math":false,"creators":["Gamarallage, Anuththari"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Milenkovic, Olgica"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-08-26T21:54:49Z","date_published":"2020-08-26T21:54:49Z","updated_at":"2026-07-22T22:24:47Z","subjects":["motif prediction","graph generative models"],"languages":["en"],"rights":["Copyright 2020 Anuththari Gamarallage"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/107976","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Milenkovic, Olgica"]},{"key":"dc:creator","label":"Author","values":["Gamarallage, Anuththari"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-08-26T21:54:49Z","2020-05-05","2020-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"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":["motif prediction","graph generative models"]}]},{"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 Anuththari Gamarallage"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/107976"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Graphs are commonly used to represent pairwise interactions between different entities in networks. Generative graph models create new graphs that mimic the properties of already existing graphs. Generative models are successful at retaining the pairwise interactions of the underlying networks but often fail to capture higher-order connectivity patterns between more than two entities. A network motif is one such pattern observed in various realworld networks. Different types of graphs contain different network motifs, an example of which are triangles that often arise in social and biological networks. Motifs model important functional properties of the graph. Hence, it is vital to capture these higher-order structures to simulate real-world networks accurately. This thesis introduces a motif-targeted graph generative model based on a generative adversarial network (GAN) architecture that generalizes and outperforms the current benchmark approach, NetGAN, at motif prediction. This model and its extension to hypergraphs are tested on real-world social and biological network data, and they are shown to be better at both capturing the underlying motif statistics in the networks as well as predicting missing motifs in incomplete networks.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-08-25 without embargo terms","The student, Anuththari Gamarallage, accepted the attached license on 2020-05-04 at 09:35.","The student, Anuththari Gamarallage, submitted this Thesis for approval on 2020-05-04 at 09:36.","This Thesis was approved for publication on 2020-05-05 at 17:14.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15184 on 2020-08-25 at 17:11:36","Made available in DSpace on 2020-08-26T21:54:49Z (GMT). No. of bitstreams: 2 GAMARALLAGE-THESIS-2020.pdf: 527681 bytes, checksum: 1ad21ec7615fb652b619be162a5ecc11 (MD5) LICENSE.txt: 4212 bytes, checksum: 15d68b720e0f56d31ae7968f88fccd63 (MD5) Previous issue date: 2020-05-05"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Network motif prediction using generative models for graphs"]}]}],"canonical_facts":{"dc:contributor":["Milenkovic, Olgica"],"dc:creator":["Gamarallage, Anuththari"],"dc:date":["2020-08-26T21:54:49Z","2020-05-05","2020-05"],"dc:description":["Graphs are commonly used to represent pairwise interactions between different entities in networks. Generative graph models create new graphs that mimic the properties of already existing graphs. Generative models are successful at retaining the pairwise interactions of the underlying networks but often fail to capture higher-order connectivity patterns between more than two entities. A network motif is one such pattern observed in various realworld networks. Different types of graphs contain different network motifs, an example of which are triangles that often arise in social and biological networks. Motifs model important functional properties of the graph. Hence, it is vital to capture these higher-order structures to simulate real-world networks accurately. This thesis introduces a motif-targeted graph generative model based on a generative adversarial network (GAN) architecture that generalizes and outperforms the current benchmark approach, NetGAN, at motif prediction. This model and its extension to hypergraphs are tested on real-world social and biological network data, and they are shown to be better at both capturing the underlying motif statistics in the networks as well as predicting missing motifs in incomplete networks.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-08-25 without embargo terms","The student, Anuththari Gamarallage, accepted the attached license on 2020-05-04 at 09:35.","The student, Anuththari Gamarallage, submitted this Thesis for approval on 2020-05-04 at 09:36.","This Thesis was approved for publication on 2020-05-05 at 17:14.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15184 on 2020-08-25 at 17:11:36","Made available in DSpace on 2020-08-26T21:54:49Z (GMT). No. of bitstreams: 2 GAMARALLAGE-THESIS-2020.pdf: 527681 bytes, checksum: 1ad21ec7615fb652b619be162a5ecc11 (MD5) LICENSE.txt: 4212 bytes, checksum: 15d68b720e0f56d31ae7968f88fccd63 (MD5) Previous issue date: 2020-05-05"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/107976"],"dc:language":["en"],"dc:rights":["Copyright 2020 Anuththari Gamarallage"],"dc:subject":["motif prediction","graph generative models"],"dc:title":["Network motif prediction using generative models for graphs"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:47Z"}