Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287330167> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4287330167 abstract "Graph neural networks (GNNs) work well when the graph structure is provided. However, this structure may not always be available in real-world applications. One solution to this problem is to infer a task-specific latent structure and then apply a GNN to the inferred graph. Unfortunately, the space of possible graph structures grows super-exponentially with the number of nodes and so the task-specific supervision may be insufficient for learning both the structure and the GNN parameters. In this work, we propose the Simultaneous Learning of Adjacency and GNN Parameters with Self-supervision, or SLAPS, a method that provides more supervision for inferring a graph structure through self-supervision. A comprehensive experimental study demonstrates that SLAPS scales to large graphs with hundreds of thousands of nodes and outperforms several models that have been proposed to learn a task-specific graph structure on established benchmarks." @default.
- W4287330167 created "2022-07-25" @default.
- W4287330167 creator A5049090525 @default.
- W4287330167 creator A5063661444 @default.
- W4287330167 creator A5065918431 @default.
- W4287330167 date "2021-02-09" @default.
- W4287330167 modified "2023-09-23" @default.
- W4287330167 title "SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks" @default.
- W4287330167 doi "https://doi.org/10.48550/arxiv.2102.05034" @default.
- W4287330167 hasPublicationYear "2021" @default.
- W4287330167 type Work @default.
- W4287330167 citedByCount "0" @default.
- W4287330167 crossrefType "posted-content" @default.
- W4287330167 hasAuthorship W4287330167A5049090525 @default.
- W4287330167 hasAuthorship W4287330167A5063661444 @default.
- W4287330167 hasAuthorship W4287330167A5065918431 @default.
- W4287330167 hasBestOaLocation W42873301671 @default.
- W4287330167 hasConcept C110484373 @default.
- W4287330167 hasConcept C11413529 @default.
- W4287330167 hasConcept C119857082 @default.
- W4287330167 hasConcept C127413603 @default.
- W4287330167 hasConcept C132525143 @default.
- W4287330167 hasConcept C154945302 @default.
- W4287330167 hasConcept C201995342 @default.
- W4287330167 hasConcept C2780451532 @default.
- W4287330167 hasConcept C2988224531 @default.
- W4287330167 hasConcept C41008148 @default.
- W4287330167 hasConcept C80444323 @default.
- W4287330167 hasConceptScore W4287330167C110484373 @default.
- W4287330167 hasConceptScore W4287330167C11413529 @default.
- W4287330167 hasConceptScore W4287330167C119857082 @default.
- W4287330167 hasConceptScore W4287330167C127413603 @default.
- W4287330167 hasConceptScore W4287330167C132525143 @default.
- W4287330167 hasConceptScore W4287330167C154945302 @default.
- W4287330167 hasConceptScore W4287330167C201995342 @default.
- W4287330167 hasConceptScore W4287330167C2780451532 @default.
- W4287330167 hasConceptScore W4287330167C2988224531 @default.
- W4287330167 hasConceptScore W4287330167C41008148 @default.
- W4287330167 hasConceptScore W4287330167C80444323 @default.
- W4287330167 hasLocation W42873301671 @default.
- W4287330167 hasOpenAccess W4287330167 @default.
- W4287330167 hasPrimaryLocation W42873301671 @default.
- W4287330167 hasRelatedWork W1997448565 @default.
- W4287330167 hasRelatedWork W2081647779 @default.
- W4287330167 hasRelatedWork W2961085424 @default.
- W4287330167 hasRelatedWork W3046775127 @default.
- W4287330167 hasRelatedWork W4285260836 @default.
- W4287330167 hasRelatedWork W4286629047 @default.
- W4287330167 hasRelatedWork W4306321456 @default.
- W4287330167 hasRelatedWork W4306674287 @default.
- W4287330167 hasRelatedWork W89898052 @default.
- W4287330167 hasRelatedWork W4224009465 @default.
- W4287330167 isParatext "false" @default.
- W4287330167 isRetracted "false" @default.
- W4287330167 workType "article" @default.