Matches in SemOpenAlex for { <https://semopenalex.org/work/W2752985199> ?p ?o ?g. }
- W2752985199 endingPage "28" @default.
- W2752985199 startingPage "1" @default.
- W2752985199 abstract "Most existing active learning studies focus on designing sample selection algorithms. However, several fundamental problems deserve investigation to provide deep insight into active learning. In this article, we conduct an in-depth investigation on active learning for classification from the perspective of model change. We derive a general active learning framework for classification called maximum model change (MMC), which aims at querying the influential examples. The model change is quantified as the difference between the model parameters before and after training with the expanded training set. Inspired by the stochastic gradient update rule, the gradient of the loss with respect to a given candidate example is adopted to approximate the model change. This framework is applied to two popular classifiers: support vector machines and logistic regression. We analyze the convergence property of MMC and theoretically justify it. We explore the connection between MMC and uncertainty-based sampling to provide a uniform view. In addition, we discuss its potential usability to other learning models and show its applicability in a wide range of applications. We validate the MMC strategy on two kinds of benchmark datasets, the UCI repository and ImageNet, and show that it outperforms many state-of-the-art methods." @default.
- W2752985199 created "2017-09-15" @default.
- W2752985199 creator A5006694734 @default.
- W2752985199 creator A5018733173 @default.
- W2752985199 creator A5050174875 @default.
- W2752985199 creator A5051338992 @default.
- W2752985199 creator A5053111031 @default.
- W2752985199 creator A5071899499 @default.
- W2752985199 creator A5077967587 @default.
- W2752985199 date "2017-08-31" @default.
- W2752985199 modified "2023-10-16" @default.
- W2752985199 title "Active Learning for Classification with Maximum Model Change" @default.
- W2752985199 cites W1483994939 @default.
- W2752985199 cites W1496616155 @default.
- W2752985199 cites W1528361845 @default.
- W2752985199 cites W1599935123 @default.
- W2752985199 cites W1978633512 @default.
- W2752985199 cites W1993615002 @default.
- W2752985199 cites W2012878613 @default.
- W2752985199 cites W2016405781 @default.
- W2752985199 cites W2021367230 @default.
- W2752985199 cites W2021732807 @default.
- W2752985199 cites W2026386069 @default.
- W2752985199 cites W2029237784 @default.
- W2752985199 cites W2034124008 @default.
- W2752985199 cites W2042932437 @default.
- W2752985199 cites W2078887230 @default.
- W2752985199 cites W2088476822 @default.
- W2752985199 cites W2098203240 @default.
- W2752985199 cites W2114232233 @default.
- W2752985199 cites W2125398996 @default.
- W2752985199 cites W2128905604 @default.
- W2752985199 cites W2135012301 @default.
- W2752985199 cites W2135733005 @default.
- W2752985199 cites W2136627475 @default.
- W2752985199 cites W2138079527 @default.
- W2752985199 cites W2139212933 @default.
- W2752985199 cites W2140524605 @default.
- W2752985199 cites W2150621701 @default.
- W2752985199 cites W2153635508 @default.
- W2752985199 cites W2157958821 @default.
- W2752985199 cites W2166704235 @default.
- W2752985199 cites W2169027522 @default.
- W2752985199 cites W2171671120 @default.
- W2752985199 cites W2262342046 @default.
- W2752985199 cites W2911964244 @default.
- W2752985199 cites W2949071206 @default.
- W2752985199 cites W2951911250 @default.
- W2752985199 cites W2997980557 @default.
- W2752985199 cites W4230674625 @default.
- W2752985199 cites W4239518533 @default.
- W2752985199 doi "https://doi.org/10.1145/3086820" @default.
- W2752985199 hasPublicationYear "2017" @default.
- W2752985199 type Work @default.
- W2752985199 sameAs 2752985199 @default.
- W2752985199 citedByCount "21" @default.
- W2752985199 countsByYear W27529851992018 @default.
- W2752985199 countsByYear W27529851992019 @default.
- W2752985199 countsByYear W27529851992020 @default.
- W2752985199 countsByYear W27529851992021 @default.
- W2752985199 countsByYear W27529851992022 @default.
- W2752985199 countsByYear W27529851992023 @default.
- W2752985199 crossrefType "journal-article" @default.
- W2752985199 hasAuthorship W2752985199A5006694734 @default.
- W2752985199 hasAuthorship W2752985199A5018733173 @default.
- W2752985199 hasAuthorship W2752985199A5050174875 @default.
- W2752985199 hasAuthorship W2752985199A5051338992 @default.
- W2752985199 hasAuthorship W2752985199A5053111031 @default.
- W2752985199 hasAuthorship W2752985199A5071899499 @default.
- W2752985199 hasAuthorship W2752985199A5077967587 @default.
- W2752985199 hasConcept C107457646 @default.
- W2752985199 hasConcept C119857082 @default.
- W2752985199 hasConcept C120665830 @default.
- W2752985199 hasConcept C121332964 @default.
- W2752985199 hasConcept C12267149 @default.
- W2752985199 hasConcept C124101348 @default.
- W2752985199 hasConcept C12713177 @default.
- W2752985199 hasConcept C13280743 @default.
- W2752985199 hasConcept C154945302 @default.
- W2752985199 hasConcept C162324750 @default.
- W2752985199 hasConcept C170130773 @default.
- W2752985199 hasConcept C177264268 @default.
- W2752985199 hasConcept C185592680 @default.
- W2752985199 hasConcept C185798385 @default.
- W2752985199 hasConcept C192209626 @default.
- W2752985199 hasConcept C198531522 @default.
- W2752985199 hasConcept C199360897 @default.
- W2752985199 hasConcept C205649164 @default.
- W2752985199 hasConcept C2777303404 @default.
- W2752985199 hasConcept C41008148 @default.
- W2752985199 hasConcept C43617362 @default.
- W2752985199 hasConcept C50522688 @default.
- W2752985199 hasConcept C77967617 @default.
- W2752985199 hasConceptScore W2752985199C107457646 @default.
- W2752985199 hasConceptScore W2752985199C119857082 @default.
- W2752985199 hasConceptScore W2752985199C120665830 @default.
- W2752985199 hasConceptScore W2752985199C121332964 @default.
- W2752985199 hasConceptScore W2752985199C12267149 @default.