Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381567894> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4381567894 abstract "Spatial-temporal graph learning has emerged as a promising solution for modeling structured spatial-temporal data and learning region representations for various urban sensing tasks such as crime forecasting and traffic flow prediction. However, most existing models are vulnerable to the quality of the generated region graph due to the inaccurate graph-structured information aggregation schema. The ubiquitous spatial-temporal data noise and incompleteness in real-life scenarios pose challenges in generating high-quality region representations. To address this challenge, we propose a new spatial-temporal graph learning model (GraphST) for enabling effective self-supervised learning. Our proposed model is an adversarial contrastive learning paradigm that automates the distillation of crucial multi-view self-supervised information for robust spatial-temporal graph augmentation. We empower GraphST to adaptively identify hard samples for better self-supervision, enhancing the representation discrimination ability and robustness. In addition, we introduce a cross-view contrastive learning paradigm to model the inter-dependencies across view-specific region representations and preserve underlying relation heterogeneity. We demonstrate the superiority of our proposed GraphST method in various spatial-temporal prediction tasks on real-life datasets. We release our model implementation via the link: url{https://github.com/HKUDS/GraphST}." @default.
- W4381567894 created "2023-06-22" @default.
- W4381567894 creator A5019844880 @default.
- W4381567894 creator A5025130883 @default.
- W4381567894 creator A5044210709 @default.
- W4381567894 creator A5052267876 @default.
- W4381567894 creator A5081611476 @default.
- W4381567894 creator A5091518548 @default.
- W4381567894 date "2023-06-18" @default.
- W4381567894 modified "2023-09-24" @default.
- W4381567894 title "Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation" @default.
- W4381567894 doi "https://doi.org/10.48550/arxiv.2306.10683" @default.
- W4381567894 hasPublicationYear "2023" @default.
- W4381567894 type Work @default.
- W4381567894 citedByCount "0" @default.
- W4381567894 crossrefType "posted-content" @default.
- W4381567894 hasAuthorship W4381567894A5019844880 @default.
- W4381567894 hasAuthorship W4381567894A5025130883 @default.
- W4381567894 hasAuthorship W4381567894A5044210709 @default.
- W4381567894 hasAuthorship W4381567894A5052267876 @default.
- W4381567894 hasAuthorship W4381567894A5081611476 @default.
- W4381567894 hasAuthorship W4381567894A5091518548 @default.
- W4381567894 hasBestOaLocation W43815678941 @default.
- W4381567894 hasConcept C104317684 @default.
- W4381567894 hasConcept C119857082 @default.
- W4381567894 hasConcept C132525143 @default.
- W4381567894 hasConcept C154945302 @default.
- W4381567894 hasConcept C185592680 @default.
- W4381567894 hasConcept C37736160 @default.
- W4381567894 hasConcept C41008148 @default.
- W4381567894 hasConcept C55493867 @default.
- W4381567894 hasConcept C59404180 @default.
- W4381567894 hasConcept C63479239 @default.
- W4381567894 hasConcept C80444323 @default.
- W4381567894 hasConceptScore W4381567894C104317684 @default.
- W4381567894 hasConceptScore W4381567894C119857082 @default.
- W4381567894 hasConceptScore W4381567894C132525143 @default.
- W4381567894 hasConceptScore W4381567894C154945302 @default.
- W4381567894 hasConceptScore W4381567894C185592680 @default.
- W4381567894 hasConceptScore W4381567894C37736160 @default.
- W4381567894 hasConceptScore W4381567894C41008148 @default.
- W4381567894 hasConceptScore W4381567894C55493867 @default.
- W4381567894 hasConceptScore W4381567894C59404180 @default.
- W4381567894 hasConceptScore W4381567894C63479239 @default.
- W4381567894 hasConceptScore W4381567894C80444323 @default.
- W4381567894 hasLocation W43815678941 @default.
- W4381567894 hasOpenAccess W4381567894 @default.
- W4381567894 hasPrimaryLocation W43815678941 @default.
- W4381567894 hasRelatedWork W2952919291 @default.
- W4381567894 hasRelatedWork W3035729345 @default.
- W4381567894 hasRelatedWork W3193857078 @default.
- W4381567894 hasRelatedWork W3208304128 @default.
- W4381567894 hasRelatedWork W4225526255 @default.
- W4381567894 hasRelatedWork W4287549955 @default.
- W4381567894 hasRelatedWork W4306177400 @default.
- W4381567894 hasRelatedWork W4311734044 @default.
- W4381567894 hasRelatedWork W4379255972 @default.
- W4381567894 hasRelatedWork W4379258830 @default.
- W4381567894 isParatext "false" @default.
- W4381567894 isRetracted "false" @default.
- W4381567894 workType "article" @default.