Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949075744> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2949075744 abstract "As an effective data preprocessing step, feature selection has shown its effectiveness to prepare high-dimensional data for many machine learning tasks. The proliferation of high di-mension and huge volume big data, however, has brought major challenges, e.g. computation complexity and stability on noisy data, upon existing feature-selection techniques. This paper introduces a novel neural network-based feature selection architecture, dubbed Attention-based Feature Selec-tion (AFS). AFS consists of two detachable modules: an at-tention module for feature weight generation and a learning module for the problem modeling. The attention module for-mulates correlation problem among features and supervision target into a binary classification problem, supported by a shallow attention net for each feature. Feature weights are generated based on the distribution of respective feature se-lection patterns adjusted by backpropagation during the train-ing process. The detachable structure allows existing off-the-shelf models to be directly reused, which allows for much less training time, demands for the training data and requirements for expertise. A hybrid initialization method is also intro-duced to boost the selection accuracy for datasets without enough samples for feature weight generation. Experimental results show that AFS achieves the best accuracy and stability in comparison to several state-of-art feature selection algo-rithms upon both MNIST, noisy MNIST and several datasets with small samples." @default.
- W2949075744 created "2019-06-27" @default.
- W2949075744 creator A5012277801 @default.
- W2949075744 creator A5045158222 @default.
- W2949075744 creator A5081302488 @default.
- W2949075744 date "2019-02-28" @default.
- W2949075744 modified "2023-09-28" @default.
- W2949075744 title "AFS: An Attention-based mechanism for Supervised Feature Selection" @default.
- W2949075744 cites W1514535095 @default.
- W2949075744 cites W2044098745 @default.
- W2949075744 cites W2154053567 @default.
- W2949075744 cites W2158933803 @default.
- W2949075744 cites W2162724220 @default.
- W2949075744 cites W2211192759 @default.
- W2949075744 cites W2592299985 @default.
- W2949075744 cites W2742841012 @default.
- W2949075744 cites W2798110564 @default.
- W2949075744 doi "https://doi.org/10.48550/arxiv.1902.11074" @default.
- W2949075744 hasPublicationYear "2019" @default.
- W2949075744 type Work @default.
- W2949075744 sameAs 2949075744 @default.
- W2949075744 citedByCount "1" @default.
- W2949075744 countsByYear W29490757442021 @default.
- W2949075744 crossrefType "posted-content" @default.
- W2949075744 hasAuthorship W2949075744A5012277801 @default.
- W2949075744 hasAuthorship W2949075744A5045158222 @default.
- W2949075744 hasAuthorship W2949075744A5081302488 @default.
- W2949075744 hasBestOaLocation W29490757441 @default.
- W2949075744 hasConcept C10551718 @default.
- W2949075744 hasConcept C112972136 @default.
- W2949075744 hasConcept C114466953 @default.
- W2949075744 hasConcept C119857082 @default.
- W2949075744 hasConcept C124101348 @default.
- W2949075744 hasConcept C138885662 @default.
- W2949075744 hasConcept C148483581 @default.
- W2949075744 hasConcept C153180895 @default.
- W2949075744 hasConcept C154945302 @default.
- W2949075744 hasConcept C155032097 @default.
- W2949075744 hasConcept C190502265 @default.
- W2949075744 hasConcept C199360897 @default.
- W2949075744 hasConcept C2776401178 @default.
- W2949075744 hasConcept C34736171 @default.
- W2949075744 hasConcept C41008148 @default.
- W2949075744 hasConcept C41895202 @default.
- W2949075744 hasConcept C50644808 @default.
- W2949075744 hasConcept C81917197 @default.
- W2949075744 hasConceptScore W2949075744C10551718 @default.
- W2949075744 hasConceptScore W2949075744C112972136 @default.
- W2949075744 hasConceptScore W2949075744C114466953 @default.
- W2949075744 hasConceptScore W2949075744C119857082 @default.
- W2949075744 hasConceptScore W2949075744C124101348 @default.
- W2949075744 hasConceptScore W2949075744C138885662 @default.
- W2949075744 hasConceptScore W2949075744C148483581 @default.
- W2949075744 hasConceptScore W2949075744C153180895 @default.
- W2949075744 hasConceptScore W2949075744C154945302 @default.
- W2949075744 hasConceptScore W2949075744C155032097 @default.
- W2949075744 hasConceptScore W2949075744C190502265 @default.
- W2949075744 hasConceptScore W2949075744C199360897 @default.
- W2949075744 hasConceptScore W2949075744C2776401178 @default.
- W2949075744 hasConceptScore W2949075744C34736171 @default.
- W2949075744 hasConceptScore W2949075744C41008148 @default.
- W2949075744 hasConceptScore W2949075744C41895202 @default.
- W2949075744 hasConceptScore W2949075744C50644808 @default.
- W2949075744 hasConceptScore W2949075744C81917197 @default.
- W2949075744 hasLocation W29490757441 @default.
- W2949075744 hasOpenAccess W2949075744 @default.
- W2949075744 hasPrimaryLocation W29490757441 @default.
- W2949075744 hasRelatedWork W1566614651 @default.
- W2949075744 hasRelatedWork W2147393344 @default.
- W2949075744 hasRelatedWork W2296226123 @default.
- W2949075744 hasRelatedWork W2889587233 @default.
- W2949075744 hasRelatedWork W2903659352 @default.
- W2949075744 hasRelatedWork W2949075744 @default.
- W2949075744 hasRelatedWork W2980284037 @default.
- W2949075744 hasRelatedWork W3156786002 @default.
- W2949075744 hasRelatedWork W3197541072 @default.
- W2949075744 hasRelatedWork W2613950675 @default.
- W2949075744 isParatext "false" @default.
- W2949075744 isRetracted "false" @default.
- W2949075744 magId "2949075744" @default.
- W2949075744 workType "article" @default.