DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Namkyeong | ko |
dc.contributor.author | Park, Chanyoung | ko |
dc.contributor.author | Lee, Junseok | ko |
dc.date.accessioned | 2022-11-16T07:01:00Z | - |
dc.date.available | 2022-11-16T07:01:00Z | - |
dc.date.created | 2022-06-08 | - |
dc.date.created | 2022-06-08 | - |
dc.date.created | 2022-06-08 | - |
dc.date.created | 2022-06-08 | - |
dc.date.issued | 2022-02-22 | - |
dc.identifier.citation | 36th AAAI Conference on Artificial Intelligence, AAAI 2022, pp.7372 - 7380 | - |
dc.identifier.issn | 2159-5399 | - |
dc.identifier.uri | http://hdl.handle.net/10203/299761 | - |
dc.description.abstract | Inspired by the recent success of self-supervised methods applied on images, self-supervised learning on graph structured data has seen rapid growth especially centered on augmentation-based contrastive methods. However, we argue that without carefully designed augmentation techniques, augmentations on graphs may behave arbitrarily in that the underlying semantics of graphs can drastically change. As a consequence, the performance of existing augmentation-based methods is highly dependent on the choice of augmentation scheme, i.e., hyperparameters associated with augmentations. In this paper, we propose a novel augmentation-free self-supervised learning framework for graphs, named AFGRL. Specifically, we generate an alternative view of a graph by discovering nodes that share the local structural information and the global semantics with the graph. Extensive experiments towards various node-level tasks, i.e., node classification, clustering, and similarity search on various real-world datasets demonstrate the superiority of AFGRL. The source code for AFGRL is available at https://github.com/Namkyeong/AFGRL. | - |
dc.language | English | - |
dc.publisher | Association for the Advancement of Artificial Intelligence | - |
dc.title | Augmentation-Free Self-Supervised Learning on Graphs | - |
dc.type | Conference | - |
dc.identifier.wosid | 000893639100035 | - |
dc.identifier.scopusid | 2-s2.0-85147697223 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 7372 | - |
dc.citation.endingpage | 7380 | - |
dc.citation.publicationname | 36th AAAI Conference on Artificial Intelligence, AAAI 2022 | - |
dc.identifier.conferencecountry | CN | - |
dc.identifier.conferencelocation | Virtual | - |
dc.contributor.localauthor | Park, Chanyoung | - |
dc.contributor.nonIdAuthor | Lee, Namkyeong | - |
dc.contributor.nonIdAuthor | Lee, Junseok | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.