{"id":{"repo_id":"windsor","oai_identifier":"oai:uwindsor.scholaris.ca:20.500.14776/7177"},"canonical_url":"https://search.dev.ndltd.org/etd/windsor/oai:uwindsor.scholaris.ca:20.500.14776/7177","repository":{"repo_id":"windsor","name":"University of Windsor","base_url":"https://uwindsor.scholaris.ca/server/oai/request"},"display":{"title":"Attributed Graph Classification via Deep Graph Convolutional Neural Networks","abstract":"From social networks to biological networks, graphs are a natural way to represent a diverse set of real-world data. This research presents attributed graph convolutional neural network with a pooling layer (AGCP for short), a novel end-to-end deep neural network model which captures the higher-order latent attributes of weighted, labeled, undirected, attributed graphs of arbitrary size. The architecture of AGCP is an efficient variant of convolutional neural network (CNN) and has a linear filter function that convolves over the fixed topological structure of a graph to learn local and global attributes of the graph. Convolution is followed by a pooling layer that coarsens the graph while preserving the global structure of the original input graph using information gain. On the other hand, advances in high throughput technologies for next-generation sequencing have enabled machine learning research to acquire and extract knowledge from biological networks. We apply AGCP on three bioinformatics networks, ENZYMES, D&D, and GINA a graph dataset of gene interaction networks with genomic mutation attributes as the attributes of the vertices. In several experiments on these datasets, we demonstrate that AGCP yields better results in terms of classification accuracy relative to the previously proposed models by a considerable margin.","abstract_html":"From social networks to biological networks, graphs are a natural way to represent a diverse set of real-world data. This research presents attributed graph convolutional neural network with a pooling layer (AGCP for short), a novel end-to-end deep neural network model which captures the higher-order latent attributes of weighted, labeled, undirected, attributed graphs of arbitrary size. The architecture of AGCP is an efficient variant of convolutional neural network (CNN) and has a linear filter function that convolves over the fixed topological structure of a graph to learn local and global attributes of the graph. Convolution is followed by a pooling layer that coarsens the graph while preserving the global structure of the original input graph using information gain. On the other hand, advances in high throughput technologies for next-generation sequencing have enabled machine learning research to acquire and extract knowledge from biological networks. We apply AGCP on three bioinformatics networks, ENZYMES, D&D, and GINA a graph dataset of gene interaction networks with genomic mutation attributes as the attributes of the vertices. In several experiments on these datasets, we demonstrate that AGCP yields better results in terms of classification accuracy relative to the previously proposed models by a considerable margin.","abstract_has_math":false,"creators":["Suresh, Susha Pozhampallan"],"institution":"University of Windsor","degree_name":"M.Sc.","degree_level":"Masters","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["mita@uwindsor.ca"],"advisors":["Wu, Dan"],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019-11-21","date_published":"2019-11-21","updated_at":"2026-07-27T22:04:59Z","subjects":[],"languages":["en_CA"],"rights":[],"rights_urls":["http://creativecommons.org/licenses/by-nc-nd/4.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/20.500.14776/7177","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["mita@uwindsor.ca"]},{"key":"dc:contributor.advisor","label":"Advisor","values":["Wu, Dan"]},{"key":"dc:creator","label":"Author","values":["Suresh, Susha Pozhampallan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-07-03 13:59"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2019-12-19 15:59","2025-07-03T17:59:42Z"]},{"key":"dc:date.issued","label":"Date","values":["2019-11-21"]},{"key":"dc:type","label":"Dc Type","values":["info:eu-repo/semantics/masterThesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.Sc."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Windsor"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_CA"]},{"key":"dc:rights","label":"Dc Rights","values":["http://creativecommons.org/licenses/by-nc-nd/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/20.500.14776/7177"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["From social networks to biological networks, graphs are a natural way to represent a diverse set of real-world data. This research presents attributed graph convolutional neural network with a pooling layer (AGCP for short), a novel end-to-end deep neural network model which captures the higher-order latent attributes of weighted, labeled, undirected, attributed graphs of arbitrary size. The architecture of AGCP is an efficient variant of convolutional neural network (CNN) and has a linear filter function that convolves over the fixed topological structure of a graph to learn local and global attributes of the graph. Convolution is followed by a pooling layer that coarsens the graph while preserving the global structure of the original input graph using information gain. On the other hand, advances in high throughput technologies for next-generation sequencing have enabled machine learning research to acquire and extract knowledge from biological networks. We apply AGCP on three bioinformatics networks, ENZYMES, D&D, and GINA a graph dataset of gene interaction networks with genomic mutation attributes as the attributes of the vertices. In several experiments on these datasets, we demonstrate that AGCP yields better results in terms of classification accuracy relative to the previously proposed models by a considerable margin."]},{"key":"dc:title","label":"Title","values":["Attributed Graph Classification via Deep Graph Convolutional Neural Networks"]}]}],"canonical_facts":{"dc:contributor":["mita@uwindsor.ca"],"dc:contributor.advisor":["Wu, Dan"],"dc:creator":["Suresh, Susha Pozhampallan"],"dc:date.accessioned":["2025-07-03 13:59"],"dc:date.available":["2019-12-19 15:59","2025-07-03T17:59:42Z"],"dc:date.issued":["2019-11-21"],"dc:description.abstract":["From social networks to biological networks, graphs are a natural way to represent a diverse set of real-world data. This research presents attributed graph convolutional neural network with a pooling layer (AGCP for short), a novel end-to-end deep neural network model which captures the higher-order latent attributes of weighted, labeled, undirected, attributed graphs of arbitrary size. The architecture of AGCP is an efficient variant of convolutional neural network (CNN) and has a linear filter function that convolves over the fixed topological structure of a graph to learn local and global attributes of the graph. Convolution is followed by a pooling layer that coarsens the graph while preserving the global structure of the original input graph using information gain. On the other hand, advances in high throughput technologies for next-generation sequencing have enabled machine learning research to acquire and extract knowledge from biological networks. We apply AGCP on three bioinformatics networks, ENZYMES, D&D, and GINA a graph dataset of gene interaction networks with genomic mutation attributes as the attributes of the vertices. In several experiments on these datasets, we demonstrate that AGCP yields better results in terms of classification accuracy relative to the previously proposed models by a considerable margin."],"dc:identifier.uri":["https://hdl.handle.net/20.500.14776/7177"],"dc:language.iso":["en_CA"],"dc:rights":["http://creativecommons.org/licenses/by-nc-nd/4.0/"],"dc:title":["Attributed Graph Classification via Deep Graph Convolutional Neural Networks"],"dc:type":["info:eu-repo/semantics/masterThesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Masters"],"thesis:degree_name":["M.Sc."],"thesis:institution_name":["University of Windsor"]},"updated_at":"2026-07-27T22:04:59Z"}