Matches in SemOpenAlex for { <https://semopenalex.org/work/W4294002162> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4294002162 abstract "Representation learning on temporal graphs has drawn considerable research attention owing to its fundamental importance in a wide spectrum of real-world applications. Though a number of studies succeed in obtaining time-dependent representations, it still faces significant challenges. On the one hand, most of the existing methods restrict the embedding space with a certain curvature. However, the underlying geometry in fact shifts among the positive curvature hyperspherical, zero curvature Euclidean and negative curvature hyperbolic spaces in the evolvement over time. On the other hand, these methods usually require abundant labels to learn temporal representations, and thereby notably limit their wide use in the unlabeled graphs of the real applications. To bridge this gap, we make the first attempt to study the problem of self-supervised temporal graph representation learning in the general Riemannian space, supporting the time-varying curvature to shift among hyperspherical, Euclidean and hyperbolic spaces. In this paper, we present a novel self-supervised Riemannian graph neural network (SelfRGNN). Specifically, we design a curvature-varying Riemannian GNN with a theoretically grounded time encoding, and formulate a functional curvature over time to model the evolvement shifting among the positive, zero and negative curvature spaces. To enable the self-supervised learning, we propose a novel reweighting self-contrastive approach, exploring the Riemannian space itself without augmentation, and propose an edge-based self-supervised curvature learning with the Ricci curvature. Extensive experiments show the superiority of SelfRGNN, and moreover, the case study shows the time-varying curvature of temporal graph in reality." @default.
- W4294002162 created "2022-09-01" @default.
- W4294002162 creator A5000597313 @default.
- W4294002162 creator A5036357902 @default.
- W4294002162 creator A5051671090 @default.
- W4294002162 creator A5069093595 @default.
- W4294002162 date "2022-10-17" @default.
- W4294002162 modified "2023-10-10" @default.
- W4294002162 title "A Self-supervised Riemannian GNN with Time Varying Curvature for Temporal Graph Learning" @default.
- W4294002162 cites W1971215074 @default.
- W4294002162 cites W2087667141 @default.
- W4294002162 cites W2787927827 @default.
- W4294002162 cites W2808087697 @default.
- W4294002162 cites W2808856341 @default.
- W4294002162 cites W2808908091 @default.
- W4294002162 cites W2953485314 @default.
- W4294002162 cites W2997359955 @default.
- W4294002162 cites W2998313947 @default.
- W4294002162 cites W3099152386 @default.
- W4294002162 cites W3101588560 @default.
- W4294002162 cites W3104097132 @default.
- W4294002162 cites W3105705953 @default.
- W4294002162 cites W3155305352 @default.
- W4294002162 cites W3164410012 @default.
- W4294002162 cites W3187395669 @default.
- W4294002162 cites W3200912640 @default.
- W4294002162 cites W3208451974 @default.
- W4294002162 cites W4220779330 @default.
- W4294002162 cites W4224311348 @default.
- W4294002162 doi "https://doi.org/10.1145/3511808.3557222" @default.
- W4294002162 hasPublicationYear "2022" @default.
- W4294002162 type Work @default.
- W4294002162 citedByCount "3" @default.
- W4294002162 countsByYear W42940021622023 @default.
- W4294002162 crossrefType "proceedings-article" @default.
- W4294002162 hasAuthorship W4294002162A5000597313 @default.
- W4294002162 hasAuthorship W4294002162A5036357902 @default.
- W4294002162 hasAuthorship W4294002162A5051671090 @default.
- W4294002162 hasAuthorship W4294002162A5069093595 @default.
- W4294002162 hasBestOaLocation W42940021622 @default.
- W4294002162 hasConcept C11413529 @default.
- W4294002162 hasConcept C12089564 @default.
- W4294002162 hasConcept C129782007 @default.
- W4294002162 hasConcept C132525143 @default.
- W4294002162 hasConcept C154945302 @default.
- W4294002162 hasConcept C186450821 @default.
- W4294002162 hasConcept C195065555 @default.
- W4294002162 hasConcept C202444582 @default.
- W4294002162 hasConcept C2524010 @default.
- W4294002162 hasConcept C33923547 @default.
- W4294002162 hasConcept C41008148 @default.
- W4294002162 hasConcept C41608201 @default.
- W4294002162 hasConcept C80444323 @default.
- W4294002162 hasConcept C83677898 @default.
- W4294002162 hasConceptScore W4294002162C11413529 @default.
- W4294002162 hasConceptScore W4294002162C12089564 @default.
- W4294002162 hasConceptScore W4294002162C129782007 @default.
- W4294002162 hasConceptScore W4294002162C132525143 @default.
- W4294002162 hasConceptScore W4294002162C154945302 @default.
- W4294002162 hasConceptScore W4294002162C186450821 @default.
- W4294002162 hasConceptScore W4294002162C195065555 @default.
- W4294002162 hasConceptScore W4294002162C202444582 @default.
- W4294002162 hasConceptScore W4294002162C2524010 @default.
- W4294002162 hasConceptScore W4294002162C33923547 @default.
- W4294002162 hasConceptScore W4294002162C41008148 @default.
- W4294002162 hasConceptScore W4294002162C41608201 @default.
- W4294002162 hasConceptScore W4294002162C80444323 @default.
- W4294002162 hasConceptScore W4294002162C83677898 @default.
- W4294002162 hasLocation W42940021621 @default.
- W4294002162 hasLocation W42940021622 @default.
- W4294002162 hasOpenAccess W4294002162 @default.
- W4294002162 hasPrimaryLocation W42940021621 @default.
- W4294002162 hasRelatedWork W2011623603 @default.
- W4294002162 hasRelatedWork W2617943363 @default.
- W4294002162 hasRelatedWork W2787038041 @default.
- W4294002162 hasRelatedWork W3035134435 @default.
- W4294002162 hasRelatedWork W3146864044 @default.
- W4294002162 hasRelatedWork W3210523300 @default.
- W4294002162 hasRelatedWork W3211564896 @default.
- W4294002162 hasRelatedWork W4287252481 @default.
- W4294002162 hasRelatedWork W4297731700 @default.
- W4294002162 hasRelatedWork W4310978106 @default.
- W4294002162 isParatext "false" @default.
- W4294002162 isRetracted "false" @default.
- W4294002162 workType "article" @default.