Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289533954> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4289533954 abstract "Recently, graph neural network (GNN) has achieved great success in many graph learning tasks such as node classifi-cation and graph classification. However, there is no single GNN architecture that can fit different graph datasets. Designing an effective GNN for a specific graph dataset requires considerable expert experience and huge computational costs. Inspired by the success of neural architecture search (NAS), searching the GNN architectures automatically has attracted more and more attention. Motivated by the fact that the search space plays a critical role in the NAS, we propose a novel and effective graph neural architecture search method called PSP from the perspective of search space design in this paper. We first propose an expressive search space composed of multiple cells. Instead of searching the entire architecture, we focus on searching the architecture of the cell. Then, we propose a progressive space pruning-based algorithm to search the architectures efficiently. Moreover, the data-specific search spaces and architectures ob-tained by PSP can be transferred to new graph datasets based on meta-learning. Extensive experimental results on different types of graph datasets reveal that PSP outperforms the state-of-the-art handcrafted architectures and the existing NAS methods in terms of effectiveness and efficiency." @default.
- W4289533954 created "2022-08-03" @default.
- W4289533954 creator A5005377211 @default.
- W4289533954 creator A5007538828 @default.
- W4289533954 creator A5019086612 @default.
- W4289533954 creator A5031625880 @default.
- W4289533954 creator A5047957850 @default.
- W4289533954 creator A5056204625 @default.
- W4289533954 creator A5086985082 @default.
- W4289533954 date "2022-05-01" @default.
- W4289533954 modified "2023-09-27" @default.
- W4289533954 title "PSP: Progressive Space Pruning for Efficient Graph Neural Architecture Search" @default.
- W4289533954 cites W2016023958 @default.
- W4289533954 cites W2016423476 @default.
- W4289533954 cites W2027731328 @default.
- W4289533954 cites W2153959628 @default.
- W4289533954 cites W2735272571 @default.
- W4289533954 cites W2788919350 @default.
- W4289533954 cites W2912636151 @default.
- W4289533954 cites W2963653811 @default.
- W4289533954 cites W2963821229 @default.
- W4289533954 cites W2964081807 @default.
- W4289533954 cites W2965658867 @default.
- W4289533954 cites W2966284335 @default.
- W4289533954 cites W2966859223 @default.
- W4289533954 cites W2998227662 @default.
- W4289533954 cites W3034723893 @default.
- W4289533954 cites W3080510905 @default.
- W4289533954 cites W3103720336 @default.
- W4289533954 cites W3105136071 @default.
- W4289533954 cites W3164008977 @default.
- W4289533954 cites W3176189116 @default.
- W4289533954 cites W3187249216 @default.
- W4289533954 cites W4210257598 @default.
- W4289533954 doi "https://doi.org/10.1109/icde53745.2022.00208" @default.
- W4289533954 hasPublicationYear "2022" @default.
- W4289533954 type Work @default.
- W4289533954 citedByCount "1" @default.
- W4289533954 countsByYear W42895339542023 @default.
- W4289533954 crossrefType "proceedings-article" @default.
- W4289533954 hasAuthorship W4289533954A5005377211 @default.
- W4289533954 hasAuthorship W4289533954A5007538828 @default.
- W4289533954 hasAuthorship W4289533954A5019086612 @default.
- W4289533954 hasAuthorship W4289533954A5031625880 @default.
- W4289533954 hasAuthorship W4289533954A5047957850 @default.
- W4289533954 hasAuthorship W4289533954A5056204625 @default.
- W4289533954 hasAuthorship W4289533954A5086985082 @default.
- W4289533954 hasConcept C108010975 @default.
- W4289533954 hasConcept C119857082 @default.
- W4289533954 hasConcept C123657996 @default.
- W4289533954 hasConcept C132525143 @default.
- W4289533954 hasConcept C142362112 @default.
- W4289533954 hasConcept C153349607 @default.
- W4289533954 hasConcept C154945302 @default.
- W4289533954 hasConcept C41008148 @default.
- W4289533954 hasConcept C6557445 @default.
- W4289533954 hasConcept C80444323 @default.
- W4289533954 hasConcept C86803240 @default.
- W4289533954 hasConceptScore W4289533954C108010975 @default.
- W4289533954 hasConceptScore W4289533954C119857082 @default.
- W4289533954 hasConceptScore W4289533954C123657996 @default.
- W4289533954 hasConceptScore W4289533954C132525143 @default.
- W4289533954 hasConceptScore W4289533954C142362112 @default.
- W4289533954 hasConceptScore W4289533954C153349607 @default.
- W4289533954 hasConceptScore W4289533954C154945302 @default.
- W4289533954 hasConceptScore W4289533954C41008148 @default.
- W4289533954 hasConceptScore W4289533954C6557445 @default.
- W4289533954 hasConceptScore W4289533954C80444323 @default.
- W4289533954 hasConceptScore W4289533954C86803240 @default.
- W4289533954 hasFunder F4320321001 @default.
- W4289533954 hasFunder F4320322769 @default.
- W4289533954 hasLocation W42895339541 @default.
- W4289533954 hasOpenAccess W4289533954 @default.
- W4289533954 hasPrimaryLocation W42895339541 @default.
- W4289533954 hasRelatedWork W1879310460 @default.
- W4289533954 hasRelatedWork W2364531466 @default.
- W4289533954 hasRelatedWork W2961085424 @default.
- W4289533954 hasRelatedWork W3046775127 @default.
- W4289533954 hasRelatedWork W3199608561 @default.
- W4289533954 hasRelatedWork W4285260836 @default.
- W4289533954 hasRelatedWork W4286629047 @default.
- W4289533954 hasRelatedWork W4306321456 @default.
- W4289533954 hasRelatedWork W4306674287 @default.
- W4289533954 hasRelatedWork W4224009465 @default.
- W4289533954 isParatext "false" @default.
- W4289533954 isRetracted "false" @default.
- W4289533954 workType "article" @default.