Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313197385> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4313197385 abstract "Graph Neural Networks (GNNs), originally proposed for node classification, have also motivated many recent works on edge prediction (a.k.a., link prediction). However, existing methods lack elaborate design regarding the distinctions between two tasks that have been frequently overlooked: (i) edges only constitute the topology in the node classification task but can be used as both the topology and the supervisions (i.e., labels) in the edge prediction task; (ii) the node classification makes prediction over each individual node, while the edge prediction is determinated by each pair of nodes. To this end, we propose a novel edge prediction paradigm named Edge-aware Message PassIng neuRal nEtworks (EMPIRE). Concretely, we first introduce an edge splitting technique to specify use of each edge where each edge is solely used as either the topology or the supervision (named as topology edge or supervision edge). We then develop a new message passing mechanism that generates the messages to source nodes (through topology edges) being aware of target nodes (through supervision edges). In order to emphasize the differences between pairs connected by supervision edges and pairs unconnected, we further weight the messages to highlight the relative ones that can reflect the differences. In addition, we design a novel negative node-pair sampling trick that efficiently samples 'hard' negative instances in the supervision instances, and can significantly improve the performance. Experimental results verify that the proposed method can significantly outperform existing state-of-the-art models regarding the edge prediction task on multiple homogeneous and heterogeneous graph datasets." @default.
- W4313197385 created "2023-01-06" @default.
- W4313197385 creator A5015179224 @default.
- W4313197385 creator A5034967647 @default.
- W4313197385 creator A5040673285 @default.
- W4313197385 creator A5046553390 @default.
- W4313197385 creator A5057947122 @default.
- W4313197385 creator A5085016531 @default.
- W4313197385 creator A5088888083 @default.
- W4313197385 creator A5090720315 @default.
- W4313197385 date "2022-12-25" @default.
- W4313197385 modified "2023-09-27" @default.
- W4313197385 title "Refined Edge Usage of Graph Neural Networks for Edge Prediction" @default.
- W4313197385 doi "https://doi.org/10.48550/arxiv.2212.12970" @default.
- W4313197385 hasPublicationYear "2022" @default.
- W4313197385 type Work @default.
- W4313197385 citedByCount "0" @default.
- W4313197385 crossrefType "posted-content" @default.
- W4313197385 hasAuthorship W4313197385A5015179224 @default.
- W4313197385 hasAuthorship W4313197385A5034967647 @default.
- W4313197385 hasAuthorship W4313197385A5040673285 @default.
- W4313197385 hasAuthorship W4313197385A5046553390 @default.
- W4313197385 hasAuthorship W4313197385A5057947122 @default.
- W4313197385 hasAuthorship W4313197385A5085016531 @default.
- W4313197385 hasAuthorship W4313197385A5088888083 @default.
- W4313197385 hasAuthorship W4313197385A5090720315 @default.
- W4313197385 hasBestOaLocation W43131973851 @default.
- W4313197385 hasConcept C114614502 @default.
- W4313197385 hasConcept C127413603 @default.
- W4313197385 hasConcept C132525143 @default.
- W4313197385 hasConcept C154945302 @default.
- W4313197385 hasConcept C162307627 @default.
- W4313197385 hasConcept C184720557 @default.
- W4313197385 hasConcept C199845137 @default.
- W4313197385 hasConcept C201995342 @default.
- W4313197385 hasConcept C2780451532 @default.
- W4313197385 hasConcept C2984842247 @default.
- W4313197385 hasConcept C31258907 @default.
- W4313197385 hasConcept C33923547 @default.
- W4313197385 hasConcept C41008148 @default.
- W4313197385 hasConcept C50644808 @default.
- W4313197385 hasConcept C62611344 @default.
- W4313197385 hasConcept C66938386 @default.
- W4313197385 hasConcept C80444323 @default.
- W4313197385 hasConceptScore W4313197385C114614502 @default.
- W4313197385 hasConceptScore W4313197385C127413603 @default.
- W4313197385 hasConceptScore W4313197385C132525143 @default.
- W4313197385 hasConceptScore W4313197385C154945302 @default.
- W4313197385 hasConceptScore W4313197385C162307627 @default.
- W4313197385 hasConceptScore W4313197385C184720557 @default.
- W4313197385 hasConceptScore W4313197385C199845137 @default.
- W4313197385 hasConceptScore W4313197385C201995342 @default.
- W4313197385 hasConceptScore W4313197385C2780451532 @default.
- W4313197385 hasConceptScore W4313197385C2984842247 @default.
- W4313197385 hasConceptScore W4313197385C31258907 @default.
- W4313197385 hasConceptScore W4313197385C33923547 @default.
- W4313197385 hasConceptScore W4313197385C41008148 @default.
- W4313197385 hasConceptScore W4313197385C50644808 @default.
- W4313197385 hasConceptScore W4313197385C62611344 @default.
- W4313197385 hasConceptScore W4313197385C66938386 @default.
- W4313197385 hasConceptScore W4313197385C80444323 @default.
- W4313197385 hasLocation W43131973851 @default.
- W4313197385 hasOpenAccess W4313197385 @default.
- W4313197385 hasPrimaryLocation W43131973851 @default.
- W4313197385 hasRelatedWork W1856617497 @default.
- W4313197385 hasRelatedWork W2041126748 @default.
- W4313197385 hasRelatedWork W2071483494 @default.
- W4313197385 hasRelatedWork W2104386080 @default.
- W4313197385 hasRelatedWork W2162982837 @default.
- W4313197385 hasRelatedWork W2166510624 @default.
- W4313197385 hasRelatedWork W2355549421 @default.
- W4313197385 hasRelatedWork W3004161282 @default.
- W4313197385 hasRelatedWork W3204102400 @default.
- W4313197385 hasRelatedWork W335527655 @default.
- W4313197385 isParatext "false" @default.
- W4313197385 isRetracted "false" @default.
- W4313197385 workType "article" @default.