{"id":{"repo_id":"uoit","oai_identifier":"oai:ontariotechu.scholaris.ca:10155/1644"},"canonical_url":"https://search.dev.ndltd.org/etd/uoit/oai:ontariotechu.scholaris.ca:10155/1644","repository":{"repo_id":"uoit","name":"Ontario Institute of Technology","base_url":"https://ontariotechu.scholaris.ca/server/oai/request"},"display":{"title":"Subgraph classification through neighborhood pooling","abstract":"Subgraph classification is an emerging field in graph representation learning where the task is to classify a group of nodes (i.e., a subgraph) within a graph. Graph neural networks (GNNs) are the de facto solution for node, link, and graph-level tasks but fail to perform well on subgraph classification tasks. Even GNNs tailored for graph classification are not directly transferable to subgraph classification as they ignore the external topology of the subgraph, thus failing to capture how the subgraph is located within the larger graph. Existing models for subgraph classification address this shortcoming through labeling tricks or multiple message-passing channels, both of which impose a computation burden and are not scalable to large graphs. To address the scalability issue while maintaining generalization, we propose Stochastic Subgraph Neighborhood Pooling (SSNP), which jointly aggregates the subgraph and its neighborhood (i.e., external topology) information without any computationally expensive operations such as labeling tricks. To improve scalability and generalization further, we also propose a simple data augmentation pre-processing step for SSNP that creates multiple sparse views of the subgraph neighborhood. We show that our model is more expressive than plain GNNs, without using any labeling tricks. Our extensive experiments demonstrate that our models outperform current state-of-the art methods (with a margin of up to 2%) while being up to 3× faster in training.","abstract_html":"Subgraph classification is an emerging field in graph representation learning where the task is to classify a group of nodes (i.e., a subgraph) within a graph. Graph neural networks (GNNs) are the de facto solution for node, link, and graph-level tasks but fail to perform well on subgraph classification tasks. Even GNNs tailored for graph classification are not directly transferable to subgraph classification as they ignore the external topology of the subgraph, thus failing to capture how the subgraph is located within the larger graph. Existing models for subgraph classification address this shortcoming through labeling tricks or multiple message-passing channels, both of which impose a computation burden and are not scalable to large graphs. To address the scalability issue while maintaining generalization, we propose Stochastic Subgraph Neighborhood Pooling (SSNP), which jointly aggregates the subgraph and its neighborhood (i.e., external topology) information without any computationally expensive operations such as labeling tricks. To improve scalability and generalization further, we also propose a simple data augmentation pre-processing step for SSNP that creates multiple sparse views of the subgraph neighborhood. We show that our model is more expressive than plain GNNs, without using any labeling tricks. Our extensive experiments demonstrate that our models outperform current state-of-the art methods (with a margin of up to 2%) while being up to 3× faster in training.","abstract_has_math":false,"creators":["Jacob, Shweta Ann"],"institution":"University of Ontario Institute of Technology","degree_name":"Master of Science (MSc)","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Salehi-Abari, Amirali"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-06-01","date_published":"2023-06-01","updated_at":"2026-07-24T05:35:32Z","subjects":["Graph neural networks","Subgraph classification"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10155/1644","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Salehi-Abari, Amirali"]},{"key":"dc:creator","label":"Author","values":["Jacob, Shweta Ann"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-08-22T15:17:28Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-08-22T15:17:28Z"]},{"key":"dc:date.issued","label":"Date","values":["2023-06-01"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MSc)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Ontario Institute of Technology"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Graph neural networks","Subgraph classification"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10155/1644"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Subgraph classification is an emerging field in graph representation learning where the task is to classify a group of nodes (i.e., a subgraph) within a graph. Graph neural networks (GNNs) are the de facto solution for node, link, and graph-level tasks but fail to perform well on subgraph classification tasks. Even GNNs tailored for graph classification are not directly transferable to subgraph classification as they ignore the external topology of the subgraph, thus failing to capture how the subgraph is located within the larger graph. Existing models for subgraph classification address this shortcoming through labeling tricks or multiple message-passing channels, both of which impose a computation burden and are not scalable to large graphs. To address the scalability issue while maintaining generalization, we propose Stochastic Subgraph Neighborhood Pooling (SSNP), which jointly aggregates the subgraph and its neighborhood (i.e., external topology) information without any computationally expensive operations such as labeling tricks. To improve scalability and generalization further, we also propose a simple data augmentation pre-processing step for SSNP that creates multiple sparse views of the subgraph neighborhood. We show that our model is more expressive than plain GNNs, without using any labeling tricks. Our extensive experiments demonstrate that our models outperform current state-of-the art methods (with a margin of up to 2%) while being up to 3× faster in training."]},{"key":"dc:title","label":"Title","values":["Subgraph classification through neighborhood pooling"]}]}],"canonical_facts":{"dc:contributor.advisor":["Salehi-Abari, Amirali"],"dc:creator":["Jacob, Shweta Ann"],"dc:date.accessioned":["2023-08-22T15:17:28Z"],"dc:date.available":["2023-08-22T15:17:28Z"],"dc:date.issued":["2023-06-01"],"dc:description.abstract":["Subgraph classification is an emerging field in graph representation learning where the task is to classify a group of nodes (i.e., a subgraph) within a graph. Graph neural networks (GNNs) are the de facto solution for node, link, and graph-level tasks but fail to perform well on subgraph classification tasks. Even GNNs tailored for graph classification are not directly transferable to subgraph classification as they ignore the external topology of the subgraph, thus failing to capture how the subgraph is located within the larger graph. Existing models for subgraph classification address this shortcoming through labeling tricks or multiple message-passing channels, both of which impose a computation burden and are not scalable to large graphs. To address the scalability issue while maintaining generalization, we propose Stochastic Subgraph Neighborhood Pooling (SSNP), which jointly aggregates the subgraph and its neighborhood (i.e., external topology) information without any computationally expensive operations such as labeling tricks. To improve scalability and generalization further, we also propose a simple data augmentation pre-processing step for SSNP that creates multiple sparse views of the subgraph neighborhood. We show that our model is more expressive than plain GNNs, without using any labeling tricks. Our extensive experiments demonstrate that our models outperform current state-of-the art methods (with a margin of up to 2%) while being up to 3× faster in training."],"dc:identifier.uri":["https://hdl.handle.net/10155/1644"],"dc:language.iso":["en"],"dc:subject":["Graph neural networks","Subgraph classification"],"dc:title":["Subgraph classification through neighborhood pooling"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["Master of Science (MSc)"],"thesis:institution_name":["University of Ontario Institute of Technology"]},"updated_at":"2026-07-24T05:35:32Z"}