Matches in SemOpenAlex for { <https://semopenalex.org/work/W3182050873> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3182050873 abstract "Owing to the remarkable capability of extracting effective graph embeddings, graph convolutional network (GCN) and its variants have been successfully applied to a broad range of tasks, such as node classification, link prediction, and graph classification. Traditional GCN models suffer from the issues of overfitting and oversmoothing, while some recent techniques like DropEdge could alleviate these issues and thus enable the development of deep GCN. However, training GCN models is non-trivial, as it is sensitive to the choice of hyperparameters such as dropout rate and learning weight decay, especially for deep GCN models. In this paper, we aim to automate the training of GCN models through hyperparameter optimization. To be specific, we propose a self-tuning GCN approach with an alternate training algorithm, and further extend our approach by incorporating the population based training scheme. Experimental results on three benchmark datasets demonstrate the effectiveness of our approaches on optimizing multi-layer GCN, compared with several representative baselines." @default.
- W3182050873 created "2021-07-19" @default.
- W3182050873 creator A5021486404 @default.
- W3182050873 creator A5026512168 @default.
- W3182050873 creator A5036520456 @default.
- W3182050873 creator A5046576694 @default.
- W3182050873 date "2021-07-09" @default.
- W3182050873 modified "2023-09-26" @default.
- W3182050873 title "Automated Graph Learning via Population Based Self-Tuning GCN" @default.
- W3182050873 cites W2153959628 @default.
- W3182050873 cites W2624431344 @default.
- W3182050873 cites W2905224888 @default.
- W3182050873 cites W2907670343 @default.
- W3182050873 cites W2962767366 @default.
- W3182050873 cites W2963423218 @default.
- W3182050873 cites W2963804140 @default.
- W3182050873 cites W2963858333 @default.
- W3182050873 cites W2964015378 @default.
- W3182050873 cites W2964311892 @default.
- W3182050873 cites W2964915865 @default.
- W3182050873 cites W2971564650 @default.
- W3182050873 cites W2990045899 @default.
- W3182050873 cites W2996268457 @default.
- W3182050873 cites W3034492151 @default.
- W3182050873 cites W3034723893 @default.
- W3182050873 cites W3080510905 @default.
- W3182050873 cites W3081209961 @default.
- W3182050873 cites W3087896801 @default.
- W3182050873 cites W3088971166 @default.
- W3182050873 cites W3093002101 @default.
- W3182050873 cites W3100330855 @default.
- W3182050873 cites W3104240969 @default.
- W3182050873 cites W3127214617 @default.
- W3182050873 cites W3171723960 @default.
- W3182050873 doi "https://doi.org/10.48550/arxiv.2107.04713" @default.
- W3182050873 hasPublicationYear "2021" @default.
- W3182050873 type Work @default.
- W3182050873 sameAs 3182050873 @default.
- W3182050873 citedByCount "0" @default.
- W3182050873 crossrefType "posted-content" @default.
- W3182050873 hasAuthorship W3182050873A5021486404 @default.
- W3182050873 hasAuthorship W3182050873A5026512168 @default.
- W3182050873 hasAuthorship W3182050873A5036520456 @default.
- W3182050873 hasAuthorship W3182050873A5046576694 @default.
- W3182050873 hasBestOaLocation W31820508731 @default.
- W3182050873 hasConcept C119857082 @default.
- W3182050873 hasConcept C132525143 @default.
- W3182050873 hasConcept C13280743 @default.
- W3182050873 hasConcept C144024400 @default.
- W3182050873 hasConcept C149923435 @default.
- W3182050873 hasConcept C154945302 @default.
- W3182050873 hasConcept C185798385 @default.
- W3182050873 hasConcept C205649164 @default.
- W3182050873 hasConcept C22019652 @default.
- W3182050873 hasConcept C2908647359 @default.
- W3182050873 hasConcept C41008148 @default.
- W3182050873 hasConcept C50644808 @default.
- W3182050873 hasConcept C80444323 @default.
- W3182050873 hasConcept C8642999 @default.
- W3182050873 hasConceptScore W3182050873C119857082 @default.
- W3182050873 hasConceptScore W3182050873C132525143 @default.
- W3182050873 hasConceptScore W3182050873C13280743 @default.
- W3182050873 hasConceptScore W3182050873C144024400 @default.
- W3182050873 hasConceptScore W3182050873C149923435 @default.
- W3182050873 hasConceptScore W3182050873C154945302 @default.
- W3182050873 hasConceptScore W3182050873C185798385 @default.
- W3182050873 hasConceptScore W3182050873C205649164 @default.
- W3182050873 hasConceptScore W3182050873C22019652 @default.
- W3182050873 hasConceptScore W3182050873C2908647359 @default.
- W3182050873 hasConceptScore W3182050873C41008148 @default.
- W3182050873 hasConceptScore W3182050873C50644808 @default.
- W3182050873 hasConceptScore W3182050873C80444323 @default.
- W3182050873 hasConceptScore W3182050873C8642999 @default.
- W3182050873 hasLocation W31820508731 @default.
- W3182050873 hasOpenAccess W3182050873 @default.
- W3182050873 hasPrimaryLocation W31820508731 @default.
- W3182050873 hasRelatedWork W2985459377 @default.
- W3182050873 hasRelatedWork W2989932438 @default.
- W3182050873 hasRelatedWork W3081580854 @default.
- W3182050873 hasRelatedWork W3099765033 @default.
- W3182050873 hasRelatedWork W3155135229 @default.
- W3182050873 hasRelatedWork W3159087789 @default.
- W3182050873 hasRelatedWork W3175189414 @default.
- W3182050873 hasRelatedWork W4210794429 @default.
- W3182050873 hasRelatedWork W4287683259 @default.
- W3182050873 hasRelatedWork W4295309597 @default.
- W3182050873 isParatext "false" @default.
- W3182050873 isRetracted "false" @default.
- W3182050873 magId "3182050873" @default.
- W3182050873 workType "article" @default.