1. ZHAW digitalcollection
  2. School of Engineering
  3. Publikationen
  4. Publikationen School of Engineering
Full metadata record
DC FieldValueLanguage
dc.contributor.authorAli, Waqar-
dc.contributor.authorVascon, Sebastiano-
dc.contributor.authorStadelmann, Thilo-
dc.contributor.authorPelillo, Marcello-
dc.date.accessioned2023-01-23T09:58:56Z-
dc.date.available2023-01-23T09:58:56Z-
dc.date.issued2023-
dc.identifier.isbn978-1-4503-9517-5de_CH
dc.identifier.urihttps://digitalcollection.zhaw.ch/handle/11475/26685-
dc.descriptionArticle 4, 9 pagesde_CH
dc.description.abstractGraph Neural Networks (GNNs) have revolutionized graph learning through efficiently learned node embeddings and achieved promising results in various graph-related tasks such as node and graph classification. Within GNNs, a pooling operation reduces the size of the input graph by grouping nodes that share commonalities intending to generate more robust and expressive latent representations. For this reason, pooling is a critical operation that significantly affects downstream tasks. Existing global pooling methods mostly use readout functions like max or sum to perform the pooling operations, but these methods neglect the hierarchical information of graphs. Clique-based hierarchical pooling methods have recently been developed to overcome global pooling issues. Such clique pooling methods perform a hard partition between nodes, which destroys the topological structural relationship of nodes, assuming that a node should belong to a single cluster. However, overlapping clusters widely exist in many real-world networks since a node can belong to more than one cluster. Here we introduce a new hierarchical graph pooling method to address this issue. Our pooling method, named Quasi-CliquePool, builds on the concept of a quasi-clique, which generalizes the notion of cliques to extract dense incomplete subgraphs of a graph. We also introduce a soft peel-off strategy to find the overlapping cluster nodes to keep the topological structural relationship of nodes. For a fair comparison, we follow the same procedure and training settings used by state-of-the-art pooling techniques. Our experiments demonstrate that combining the Quasi-Clique Pool with existing GNN architectures yields an average improvement of 2% accuracy on four out of six graph classification benchmarks compared to other existing pooling methods.de_CH
dc.language.isoende_CH
dc.publisherAssociation for Computing Machineryde_CH
dc.rightsLicence according to publishing contractde_CH
dc.subjectGraph neural networkde_CH
dc.subjectClique relaxationde_CH
dc.subjectQuasi-cliquede_CH
dc.subjectGraph poolingde_CH
dc.subjectHierarchical poolingde_CH
dc.subject.ddc006: Spezielle Computerverfahrende_CH
dc.titleQuasi-CliquePool : hierarchical graph pooling for graph classificationde_CH
dc.typeKonferenz: Paperde_CH
dcterms.typeTextde_CH
zhaw.departementSchool of Engineeringde_CH
zhaw.organisationalunitCentre for Artificial Intelligence (CAI)de_CH
zhaw.publisher.placeNew Yorkde_CH
dc.identifier.doi10.1145/3555776.3578600de_CH
zhaw.conference.details2nd Graph Models for Learning and Recognition (GMLR 2023) Track at the 38th ACM/SIGAPP Symposium on Applied Computing (SAC 2023), Tallinn, Estonia, 27 March - 2 April 2023de_CH
zhaw.funding.euNode_CH
zhaw.originated.zhawYesde_CH
zhaw.pages.end552de_CH
zhaw.pages.start544de_CH
zhaw.publication.statuspublishedVersionde_CH
zhaw.publication.reviewPeer review (Publikation)de_CH
zhaw.title.proceedingsSAC '23: Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computingde_CH
zhaw.webfeedMachine Perception and Cognitionde_CH
zhaw.webfeedDatalabde_CH
zhaw.webfeedZHAW digitalde_CH
zhaw.author.additionalNode_CH
zhaw.display.portraitYesde_CH
Appears in collections:Publikationen School of Engineering

Files in This Item:
There are no files associated with this item.
Show simple item record
Ali, W., Vascon, S., Stadelmann, T., & Pelillo, M. (2023). Quasi-CliquePool : hierarchical graph pooling for graph classification [Conference paper]. SAC ’23: Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing, 544–552. https://doi.org/10.1145/3555776.3578600
Ali, W. et al. (2023) ‘Quasi-CliquePool : hierarchical graph pooling for graph classification’, in SAC ’23: Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing. New York: Association for Computing Machinery, pp. 544–552. Available at: https://doi.org/10.1145/3555776.3578600.
W. Ali, S. Vascon, T. Stadelmann, and M. Pelillo, “Quasi-CliquePool : hierarchical graph pooling for graph classification,” in SAC ’23: Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing, 2023, pp. 544–552. doi: 10.1145/3555776.3578600.
ALI, Waqar, Sebastiano VASCON, Thilo STADELMANN und Marcello PELILLO, 2023. Quasi-CliquePool : hierarchical graph pooling for graph classification. In: SAC ’23: Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing. Conference paper. New York: Association for Computing Machinery. 2023. S. 544–552. ISBN 978-1-4503-9517-5
Ali, Waqar, Sebastiano Vascon, Thilo Stadelmann, and Marcello Pelillo. 2023. “Quasi-CliquePool : Hierarchical Graph Pooling for Graph Classification.” Conference paper. In SAC ’23: Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing, 544–52. New York: Association for Computing Machinery. https://doi.org/10.1145/3555776.3578600.
Ali, Waqar, et al. “Quasi-CliquePool : Hierarchical Graph Pooling for Graph Classification.” SAC ’23: Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing, Association for Computing Machinery, 2023, pp. 544–52, https://doi.org/10.1145/3555776.3578600.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.