FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308888929> ?p ?o ?g. }

• W4308888929 endingPage "105126" @default.
• W4308888929 startingPage "105126" @default.
• W4308888929 abstract "Weighted nearest neighbors (WNN) classifiers are popular non-parametric classifiers. Despite the significant progress in WNN, most existing WNN classifiers are designed for traditional supervised learning problems where both training samples and test samples are assumed to be independent and identically distributed. However, in many real applications, it could be difficult or expensive to obtain training samples from the distribution of interest. Therefore, data collected from some related distributions are often used as supplementary training data for the classification task under the distribution of interest. It is essential to develop effective classification methods that could incorporate both training samples from the distribution of interest (if they exist) and supplementary training samples from a different but related distribution. To address this challenge, we propose a novel Transfer learning weighted Nearest Neighbors (TNN) classifier. As a WNN classifier, TNN determines the weights on the class labels of training samples for different test samples adaptively by minimizing an upper bound on the conditional expectation of the estimation error of the regression function. It puts decreasing weights on the class labels of the successive more distant neighbors. To accommodate the difference between training samples from the distribution of interest and supplementary training samples, TNN adds a non-negative offset to the distance between each supplementary training sample and the test sample, and thus constrains the excessive influence of the supplementary training samples on the prediction. Our theoretical studies show that, under certain conditions, TNN is consistent and minimax optimal (up to a logarithmic factor) in the covariate shift setting. In the posterior drift or the more general setting where both covariate shift and posterior drift exist, the excess risk of TNN depends on the maximum posterior discrepancy between the distribution of the supplementary training samples and the distribution of interest. Both our simulation studies and an application to the land use/land cover mapping problem in geography demonstrate that TNN outperforms other existing methods. It can serve as an effective tool for transfer learning." @default.
• W4308888929 created "2022-11-18" @default.
• W4308888929 creator A5023289798 @default.
• W4308888929 creator A5084397928 @default.
• W4308888929 date "2023-01-01" @default.
• W4308888929 modified "2023-09-24" @default.
• W4308888929 title "TNN: A transfer learning classifier based on weighted nearest neighbors" @default.
• W4308888929 cites W1996437515 @default.
• W4308888929 cites W2004089144 @default.
• W4308888929 cites W2034368206 @default.
• W4308888929 cites W2035954132 @default.
• W4308888929 cites W2043919728 @default.
• W4308888929 cites W2062291443 @default.
• W4308888929 cites W2081454259 @default.
• W4308888929 cites W2139122730 @default.
• W4308888929 cites W2238226741 @default.
• W4308888929 cites W2326104347 @default.
• W4308888929 cites W2396666837 @default.
• W4308888929 cites W2549412929 @default.
• W4308888929 cites W2964250041 @default.
• W4308888929 cites W2968726102 @default.
• W4308888929 cites W3101477643 @default.
• W4308888929 cites W3128888666 @default.
• W4308888929 cites W3133558619 @default.
• W4308888929 cites W4206657242 @default.
• W4308888929 doi "https://doi.org/10.1016/j.jmva.2022.105126" @default.
• W4308888929 hasPublicationYear "2023" @default.
• W4308888929 type Work @default.
• W4308888929 citedByCount "0" @default.
• W4308888929 crossrefType "journal-article" @default.
• W4308888929 hasAuthorship W4308888929A5023289798 @default.
• W4308888929 hasAuthorship W4308888929A5084397928 @default.
• W4308888929 hasBestOaLocation W43088889291 @default.
• W4308888929 hasConcept C105795698 @default.
• W4308888929 hasConcept C117251300 @default.
• W4308888929 hasConcept C119857082 @default.
• W4308888929 hasConcept C126255220 @default.
• W4308888929 hasConcept C149728462 @default.
• W4308888929 hasConcept C153180895 @default.
• W4308888929 hasConcept C154945302 @default.
• W4308888929 hasConcept C33923547 @default.
• W4308888929 hasConcept C41008148 @default.
• W4308888929 hasConcept C95623464 @default.
• W4308888929 hasConceptScore W4308888929C105795698 @default.
• W4308888929 hasConceptScore W4308888929C117251300 @default.
• W4308888929 hasConceptScore W4308888929C119857082 @default.
• W4308888929 hasConceptScore W4308888929C126255220 @default.
• W4308888929 hasConceptScore W4308888929C149728462 @default.
• W4308888929 hasConceptScore W4308888929C153180895 @default.
• W4308888929 hasConceptScore W4308888929C154945302 @default.
• W4308888929 hasConceptScore W4308888929C33923547 @default.
• W4308888929 hasConceptScore W4308888929C41008148 @default.
• W4308888929 hasConceptScore W4308888929C95623464 @default.
• W4308888929 hasLocation W43088889291 @default.
• W4308888929 hasOpenAccess W4308888929 @default.
• W4308888929 hasPrimaryLocation W43088889291 @default.
• W4308888929 hasRelatedWork W2001652754 @default.
• W4308888929 hasRelatedWork W2379065761 @default.
• W4308888929 hasRelatedWork W2549006548 @default.
• W4308888929 hasRelatedWork W2807311372 @default.
• W4308888929 hasRelatedWork W2921036759 @default.
• W4308888929 hasRelatedWork W2961085424 @default.
• W4308888929 hasRelatedWork W2972035100 @default.
• W4308888929 hasRelatedWork W3043252291 @default.
• W4308888929 hasRelatedWork W4214932115 @default.
• W4308888929 hasRelatedWork W3158004940 @default.
• W4308888929 hasVolume "193" @default.
• W4308888929 isParatext "false" @default.
• W4308888929 isRetracted "false" @default.
• W4308888929 workType "article" @default.