Matches in SemOpenAlex for { <https://semopenalex.org/work/W4323360692> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4323360692 abstract "Many graph neural networks have been developed to learn graph representations in either Euclidean or hyperbolic space, with all nodes' representations embedded in a single space. However, a graph can have hyperbolic and Euclidean geometries at different regions of the graph. Thus, it is sub-optimal to indifferently embed an entire graph into a single space. In this paper, we explore and analyze two notions of local hyperbolicity, describing the underlying local geometry: geometric (Gromov) and model-based, to determine the preferred space of embedding for each node. The two hyperbolicities' distributions are aligned using the Wasserstein metric such that the calculated geometric hyperbolicity guides the choice of the learned model hyperbolicity. As such our model Joint Space Graph Neural Network (JSGNN) can leverage both Euclidean and hyperbolic spaces during learning by allowing node-specific geometry space selection. We evaluate our model on both node classification and link prediction tasks and observe promising performance compared to baseline models." @default.
- W4323360692 created "2023-03-08" @default.
- W4323360692 creator A5027080862 @default.
- W4323360692 creator A5046850399 @default.
- W4323360692 creator A5065494925 @default.
- W4323360692 date "2023-03-03" @default.
- W4323360692 modified "2023-10-16" @default.
- W4323360692 title "Node-Specific Space Selection via Localized Geometric Hyperbolicity in Graph Neural Networks" @default.
- W4323360692 doi "https://doi.org/10.48550/arxiv.2303.01724" @default.
- W4323360692 hasPublicationYear "2023" @default.
- W4323360692 type Work @default.
- W4323360692 citedByCount "0" @default.
- W4323360692 crossrefType "posted-content" @default.
- W4323360692 hasAuthorship W4323360692A5027080862 @default.
- W4323360692 hasAuthorship W4323360692A5046850399 @default.
- W4323360692 hasAuthorship W4323360692A5065494925 @default.
- W4323360692 hasBestOaLocation W43233606921 @default.
- W4323360692 hasConcept C114614502 @default.
- W4323360692 hasConcept C118615104 @default.
- W4323360692 hasConcept C129782007 @default.
- W4323360692 hasConcept C132525143 @default.
- W4323360692 hasConcept C153083717 @default.
- W4323360692 hasConcept C154945302 @default.
- W4323360692 hasConcept C184720557 @default.
- W4323360692 hasConcept C186450821 @default.
- W4323360692 hasConcept C198043062 @default.
- W4323360692 hasConcept C202444582 @default.
- W4323360692 hasConcept C203776342 @default.
- W4323360692 hasConcept C22149727 @default.
- W4323360692 hasConcept C2524010 @default.
- W4323360692 hasConcept C30609935 @default.
- W4323360692 hasConcept C33923547 @default.
- W4323360692 hasConcept C41008148 @default.
- W4323360692 hasConcept C41608201 @default.
- W4323360692 hasConcept C49777392 @default.
- W4323360692 hasConcept C50644808 @default.
- W4323360692 hasConcept C53471067 @default.
- W4323360692 hasConcept C80444323 @default.
- W4323360692 hasConcept C83677898 @default.
- W4323360692 hasConcept C88230418 @default.
- W4323360692 hasConceptScore W4323360692C114614502 @default.
- W4323360692 hasConceptScore W4323360692C118615104 @default.
- W4323360692 hasConceptScore W4323360692C129782007 @default.
- W4323360692 hasConceptScore W4323360692C132525143 @default.
- W4323360692 hasConceptScore W4323360692C153083717 @default.
- W4323360692 hasConceptScore W4323360692C154945302 @default.
- W4323360692 hasConceptScore W4323360692C184720557 @default.
- W4323360692 hasConceptScore W4323360692C186450821 @default.
- W4323360692 hasConceptScore W4323360692C198043062 @default.
- W4323360692 hasConceptScore W4323360692C202444582 @default.
- W4323360692 hasConceptScore W4323360692C203776342 @default.
- W4323360692 hasConceptScore W4323360692C22149727 @default.
- W4323360692 hasConceptScore W4323360692C2524010 @default.
- W4323360692 hasConceptScore W4323360692C30609935 @default.
- W4323360692 hasConceptScore W4323360692C33923547 @default.
- W4323360692 hasConceptScore W4323360692C41008148 @default.
- W4323360692 hasConceptScore W4323360692C41608201 @default.
- W4323360692 hasConceptScore W4323360692C49777392 @default.
- W4323360692 hasConceptScore W4323360692C50644808 @default.
- W4323360692 hasConceptScore W4323360692C53471067 @default.
- W4323360692 hasConceptScore W4323360692C80444323 @default.
- W4323360692 hasConceptScore W4323360692C83677898 @default.
- W4323360692 hasConceptScore W4323360692C88230418 @default.
- W4323360692 hasLocation W43233606921 @default.
- W4323360692 hasOpenAccess W4323360692 @default.
- W4323360692 hasPrimaryLocation W43233606921 @default.
- W4323360692 hasRelatedWork W2618798060 @default.
- W4323360692 hasRelatedWork W2962936818 @default.
- W4323360692 hasRelatedWork W3082644980 @default.
- W4323360692 hasRelatedWork W3146864044 @default.
- W4323360692 hasRelatedWork W3187974408 @default.
- W4323360692 hasRelatedWork W3210523300 @default.
- W4323360692 hasRelatedWork W4225304485 @default.
- W4323360692 hasRelatedWork W4287252481 @default.
- W4323360692 hasRelatedWork W4289785415 @default.
- W4323360692 hasRelatedWork W4290945646 @default.
- W4323360692 isParatext "false" @default.
- W4323360692 isRetracted "false" @default.
- W4323360692 workType "article" @default.