Publications

Detailed Information

Model-Agnostic Augmentation for Accurate Graph Classification

DC Field Value Language
dc.contributor.authorYoo, Jaemin-
dc.contributor.authorShim, Sooyeon-
dc.contributor.authorKang, U.-
dc.date.accessioned2022-09-30T05:49:23Z-
dc.date.available2022-09-30T05:49:23Z-
dc.date.created2022-08-26-
dc.date.issued2022-04-
dc.identifier.citationWWW 2022 - Proceedings of the ACM Web Conference 2022, pp.1281-1291-
dc.identifier.urihttps://hdl.handle.net/10371/184817-
dc.description.abstract© 2022 ACM.Given a graph dataset, how can we augment it for accurate graph classification? Graph augmentation is an essential strategy to improve the performance of graph-based tasks, and has been widely utilized for analyzing web and social graphs. However, previous works for graph augmentation either a) involve the target model in the process of augmentation, losing the generalizability to other tasks, or b) rely on simple heuristics that lead to unreliable results. In this work, we introduce five desired properties for effective augmentation. Then, we propose NodeSam (Node Split and Merge) and SubMix (Subgraph Mix), two model-agnostic algorithms for graph augmentation that satisfy all desired properties with different motivations. NodeSam makes a balanced change of the graph structure to minimize the risk of semantic change, while SubMix mixes random subgraphs of multiple graphs to create rich soft labels combining the evidence for different classes. Our experiments on social networks and molecular graphs show that NodeSam and SubMix outperform existing approaches in graph classification.-
dc.language영어-
dc.publisherAssociation for Computing Machinery, Inc-
dc.titleModel-Agnostic Augmentation for Accurate Graph Classification-
dc.typeArticle-
dc.identifier.doi10.1145/3485447.3512175-
dc.citation.journaltitleWWW 2022 - Proceedings of the ACM Web Conference 2022-
dc.identifier.scopusid2-s2.0-85129786320-
dc.citation.endpage1291-
dc.citation.startpage1281-
dc.description.isOpenAccessN-
dc.contributor.affiliatedAuthorKang, U.-
dc.type.docTypeConference Paper-
dc.description.journalClass1-
Appears in Collections:
Files in This Item:
There are no files associated with this item.

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share