Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366606077> ?p ?o ?g. }
- W4366606077 abstract "Abstract Motivation Feature selection is a powerful dimension reduction technique which selects a subset of relevant features for model construction. Numerous feature selection methods have been proposed, but most of them fail under the high-dimensional and low-sample size (HDLSS) setting due to the challenge of overfitting. Results We present a deep learning-based method—GRAph Convolutional nEtwork feature Selector (GRACES)—to select important features for HDLSS data. GRACES exploits latent relations between samples with various overfitting-reducing techniques to iteratively find a set of optimal features which gives rise to the greatest decreases in the optimization loss. We demonstrate that GRACES significantly outperforms other feature selection methods on both synthetic and real-world datasets. Availability and implementation The source code is publicly available at https://github.com/canc1993/graces." @default.
- W4366606077 created "2023-04-23" @default.
- W4366606077 creator A5033732758 @default.
- W4366606077 creator A5073763243 @default.
- W4366606077 creator A5079711130 @default.
- W4366606077 date "2023-04-01" @default.
- W4366606077 modified "2023-10-14" @default.
- W4366606077 title "Graph convolutional network-based feature selection for high-dimensional and low-sample size data" @default.
- W4366606077 cites W1019830208 @default.
- W4366606077 cites W1564049492 @default.
- W4366606077 cites W1987219048 @default.
- W4366606077 cites W2034029572 @default.
- W4366606077 cites W2040842850 @default.
- W4366606077 cites W2041557121 @default.
- W4366606077 cites W207758080 @default.
- W4366606077 cites W2096653978 @default.
- W4366606077 cites W2099688399 @default.
- W4366606077 cites W2104549677 @default.
- W4366606077 cites W2106398669 @default.
- W4366606077 cites W2120000263 @default.
- W4366606077 cites W2143426320 @default.
- W4366606077 cites W2143834603 @default.
- W4366606077 cites W2154053567 @default.
- W4366606077 cites W2159611475 @default.
- W4366606077 cites W2177784250 @default.
- W4366606077 cites W2253609413 @default.
- W4366606077 cites W2353267094 @default.
- W4366606077 cites W2593996946 @default.
- W4366606077 cites W2803992240 @default.
- W4366606077 cites W2911964244 @default.
- W4366606077 cites W2963799407 @default.
- W4366606077 cites W2973941913 @default.
- W4366606077 cites W2996673142 @default.
- W4366606077 cites W3085990079 @default.
- W4366606077 cites W3105003467 @default.
- W4366606077 cites W3126122061 @default.
- W4366606077 cites W3195285310 @default.
- W4366606077 cites W4200443526 @default.
- W4366606077 cites W4252684946 @default.
- W4366606077 cites W4362223627 @default.
- W4366606077 doi "https://doi.org/10.1093/bioinformatics/btad135" @default.
- W4366606077 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37084264" @default.
- W4366606077 hasPublicationYear "2023" @default.
- W4366606077 type Work @default.
- W4366606077 citedByCount "2" @default.
- W4366606077 countsByYear W43666060772023 @default.
- W4366606077 crossrefType "journal-article" @default.
- W4366606077 hasAuthorship W4366606077A5033732758 @default.
- W4366606077 hasAuthorship W4366606077A5073763243 @default.
- W4366606077 hasAuthorship W4366606077A5079711130 @default.
- W4366606077 hasBestOaLocation W43666060771 @default.
- W4366606077 hasConcept C111919701 @default.
- W4366606077 hasConcept C119857082 @default.
- W4366606077 hasConcept C124101348 @default.
- W4366606077 hasConcept C132525143 @default.
- W4366606077 hasConcept C138885662 @default.
- W4366606077 hasConcept C148483581 @default.
- W4366606077 hasConcept C153180895 @default.
- W4366606077 hasConcept C154945302 @default.
- W4366606077 hasConcept C165696696 @default.
- W4366606077 hasConcept C177264268 @default.
- W4366606077 hasConcept C199360897 @default.
- W4366606077 hasConcept C22019652 @default.
- W4366606077 hasConcept C2776401178 @default.
- W4366606077 hasConcept C2776760102 @default.
- W4366606077 hasConcept C38652104 @default.
- W4366606077 hasConcept C41008148 @default.
- W4366606077 hasConcept C41895202 @default.
- W4366606077 hasConcept C43126263 @default.
- W4366606077 hasConcept C50644808 @default.
- W4366606077 hasConcept C59404180 @default.
- W4366606077 hasConcept C70518039 @default.
- W4366606077 hasConcept C80444323 @default.
- W4366606077 hasConcept C81917197 @default.
- W4366606077 hasConceptScore W4366606077C111919701 @default.
- W4366606077 hasConceptScore W4366606077C119857082 @default.
- W4366606077 hasConceptScore W4366606077C124101348 @default.
- W4366606077 hasConceptScore W4366606077C132525143 @default.
- W4366606077 hasConceptScore W4366606077C138885662 @default.
- W4366606077 hasConceptScore W4366606077C148483581 @default.
- W4366606077 hasConceptScore W4366606077C153180895 @default.
- W4366606077 hasConceptScore W4366606077C154945302 @default.
- W4366606077 hasConceptScore W4366606077C165696696 @default.
- W4366606077 hasConceptScore W4366606077C177264268 @default.
- W4366606077 hasConceptScore W4366606077C199360897 @default.
- W4366606077 hasConceptScore W4366606077C22019652 @default.
- W4366606077 hasConceptScore W4366606077C2776401178 @default.
- W4366606077 hasConceptScore W4366606077C2776760102 @default.
- W4366606077 hasConceptScore W4366606077C38652104 @default.
- W4366606077 hasConceptScore W4366606077C41008148 @default.
- W4366606077 hasConceptScore W4366606077C41895202 @default.
- W4366606077 hasConceptScore W4366606077C43126263 @default.
- W4366606077 hasConceptScore W4366606077C50644808 @default.
- W4366606077 hasConceptScore W4366606077C59404180 @default.
- W4366606077 hasConceptScore W4366606077C70518039 @default.
- W4366606077 hasConceptScore W4366606077C80444323 @default.
- W4366606077 hasConceptScore W4366606077C81917197 @default.
- W4366606077 hasFunder F4320332161 @default.
- W4366606077 hasIssue "4" @default.
- W4366606077 hasLocation W43666060771 @default.