Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286564630> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4286564630 endingPage "815" @default.
- W4286564630 startingPage "799" @default.
- W4286564630 abstract "Graph Neural Networks (GNNs) have demonstrated state-of-the-art performance in a wide variety of analytical tasks. Current GNN approaches focus on learning representations in a Euclidean space, which are effective in capturing non-tree-like structural relations, but they fail to model complex relations in many real-world graphs, such as tree-like hierarchical graph structure. This paper instead proposes to learn representations in both Euclidean and hyperbolic spaces to model these two types of graph geometries. To this end, we introduce a novel approach – Joint hyperbolic and Euclidean geometry contrastive graph neural networks (JointGMC). JointGMC is enforced to learn multiple layer-wise optimal combinations of Euclidean and hyperbolic geometries to effectively encode diverse complex graph structures. Further, the performance of most GNNs relies heavily on the availability of large-scale manually labeled data. To mitigate this issue, JointGMC exploits proximity-based self-supervised information in different geometric spaces (i.e., Euclidean, hyperbolic, and Euclidean-hyperbolic interaction spaces) to regularize the (semi-) supervised graph learning. Extensive experimental results on eight real-world graph datasets show that JointGMC outperforms eight state-of-the-art GNN models in diverse graph mining tasks, including node classification, link prediction, and node clustering tasks, demonstrating JointGMC’s superior graph representation ability. Code is available at https://github.com/chachatang/jointgmc." @default.
- W4286564630 created "2022-07-22" @default.
- W4286564630 creator A5033050983 @default.
- W4286564630 creator A5039104219 @default.
- W4286564630 creator A5063154524 @default.
- W4286564630 creator A5091667639 @default.
- W4286564630 date "2022-09-01" @default.
- W4286564630 modified "2023-10-18" @default.
- W4286564630 title "Joint hyperbolic and Euclidean geometry contrastive graph neural networks" @default.
- W4286564630 cites W2116341502 @default.
- W4286564630 cites W2612872092 @default.
- W4286564630 cites W2952938873 @default.
- W4286564630 cites W2963224980 @default.
- W4286564630 cites W2963512530 @default.
- W4286564630 cites W3094497296 @default.
- W4286564630 cites W3096399240 @default.
- W4286564630 cites W3100993589 @default.
- W4286564630 cites W3128443161 @default.
- W4286564630 cites W3163947472 @default.
- W4286564630 cites W3164410012 @default.
- W4286564630 cites W3170895581 @default.
- W4286564630 cites W3173151551 @default.
- W4286564630 cites W3173251917 @default.
- W4286564630 cites W3173292968 @default.
- W4286564630 cites W3173511902 @default.
- W4286564630 cites W3214607848 @default.
- W4286564630 cites W3216885100 @default.
- W4286564630 cites W4210257598 @default.
- W4286564630 cites W4235484205 @default.
- W4286564630 doi "https://doi.org/10.1016/j.ins.2022.07.060" @default.
- W4286564630 hasPublicationYear "2022" @default.
- W4286564630 type Work @default.
- W4286564630 citedByCount "5" @default.
- W4286564630 countsByYear W42865646302022 @default.
- W4286564630 countsByYear W42865646302023 @default.
- W4286564630 crossrefType "journal-article" @default.
- W4286564630 hasAuthorship W4286564630A5033050983 @default.
- W4286564630 hasAuthorship W4286564630A5039104219 @default.
- W4286564630 hasAuthorship W4286564630A5063154524 @default.
- W4286564630 hasAuthorship W4286564630A5091667639 @default.
- W4286564630 hasConcept C104317684 @default.
- W4286564630 hasConcept C114614502 @default.
- W4286564630 hasConcept C120174047 @default.
- W4286564630 hasConcept C129782007 @default.
- W4286564630 hasConcept C132525143 @default.
- W4286564630 hasConcept C153180895 @default.
- W4286564630 hasConcept C154945302 @default.
- W4286564630 hasConcept C185592680 @default.
- W4286564630 hasConcept C186450821 @default.
- W4286564630 hasConcept C2524010 @default.
- W4286564630 hasConcept C33923547 @default.
- W4286564630 hasConcept C41008148 @default.
- W4286564630 hasConcept C55493867 @default.
- W4286564630 hasConcept C66746571 @default.
- W4286564630 hasConcept C80444323 @default.
- W4286564630 hasConceptScore W4286564630C104317684 @default.
- W4286564630 hasConceptScore W4286564630C114614502 @default.
- W4286564630 hasConceptScore W4286564630C120174047 @default.
- W4286564630 hasConceptScore W4286564630C129782007 @default.
- W4286564630 hasConceptScore W4286564630C132525143 @default.
- W4286564630 hasConceptScore W4286564630C153180895 @default.
- W4286564630 hasConceptScore W4286564630C154945302 @default.
- W4286564630 hasConceptScore W4286564630C185592680 @default.
- W4286564630 hasConceptScore W4286564630C186450821 @default.
- W4286564630 hasConceptScore W4286564630C2524010 @default.
- W4286564630 hasConceptScore W4286564630C33923547 @default.
- W4286564630 hasConceptScore W4286564630C41008148 @default.
- W4286564630 hasConceptScore W4286564630C55493867 @default.
- W4286564630 hasConceptScore W4286564630C66746571 @default.
- W4286564630 hasConceptScore W4286564630C80444323 @default.
- W4286564630 hasFunder F4320321001 @default.
- W4286564630 hasFunder F4320324805 @default.
- W4286564630 hasLocation W42865646301 @default.
- W4286564630 hasOpenAccess W4286564630 @default.
- W4286564630 hasPrimaryLocation W42865646301 @default.
- W4286564630 hasRelatedWork W1974892752 @default.
- W4286564630 hasRelatedWork W2004776397 @default.
- W4286564630 hasRelatedWork W2023816398 @default.
- W4286564630 hasRelatedWork W2039596978 @default.
- W4286564630 hasRelatedWork W2106751229 @default.
- W4286564630 hasRelatedWork W2783654391 @default.
- W4286564630 hasRelatedWork W2966581227 @default.
- W4286564630 hasRelatedWork W4286564630 @default.
- W4286564630 hasRelatedWork W4300891928 @default.
- W4286564630 hasRelatedWork W4327811110 @default.
- W4286564630 hasVolume "609" @default.
- W4286564630 isParatext "false" @default.
- W4286564630 isRetracted "false" @default.
- W4286564630 workType "article" @default.