Matches in SemOpenAlex for { <https://semopenalex.org/work/W3091706723> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3091706723 abstract "Most recent machine learning research focuses on developing new classifiers for the sake of improving classification accuracy. With many well-performing state-of-the-art classifiers available, there is a growing need for understanding interpretability of a classifier necessitated by practical purposes such as to find the best diet recommendation for a diabetes patient. Inverse classification is a post modeling process to find changes in input features of samples to alter the initially predicted class. It is useful in many business applications to determine how to adjust a sample input data such that the classifier predicts it to be in a desired class. In real world applications, a budget on perturbations of samples corresponding to customers or patients is usually considered, and in this setting, the number of successfully perturbed samples is key to increase benefits. In this study, we propose a new framework to solve inverse classification that maximizes the number of perturbed samples subject to a per-feature-budget limits and favorable classification classes of the perturbed samples. We design algorithms to solve this optimization problem based on gradient methods, stochastic processes, Lagrangian relaxations, and the Gumbel trick. In experiments, we find that our algorithms based on stochastic processes exhibit an excellent performance in different budget settings and they scale well." @default.
- W3091706723 created "2020-10-08" @default.
- W3091706723 creator A5013049879 @default.
- W3091706723 creator A5060826513 @default.
- W3091706723 creator A5080783529 @default.
- W3091706723 date "2020-09-29" @default.
- W3091706723 modified "2023-10-16" @default.
- W3091706723 title "Inverse Classification with Limited Budget and Maximum Number of Perturbed Samples." @default.
- W3091706723 cites W1500667213 @default.
- W3091706723 cites W1986539725 @default.
- W3091706723 cites W2079115533 @default.
- W3091706723 cites W2095577883 @default.
- W3091706723 cites W2097261433 @default.
- W3091706723 cites W2118274460 @default.
- W3091706723 cites W2155073237 @default.
- W3091706723 cites W2162800060 @default.
- W3091706723 cites W2180612164 @default.
- W3091706723 cites W2296452361 @default.
- W3091706723 cites W2296701362 @default.
- W3091706723 cites W2396881363 @default.
- W3091706723 cites W2771817472 @default.
- W3091706723 cites W2774644650 @default.
- W3091706723 cites W2804393646 @default.
- W3091706723 cites W2889862591 @default.
- W3091706723 cites W2962909570 @default.
- W3091706723 cites W2963207607 @default.
- W3091706723 cites W2963542245 @default.
- W3091706723 cites W2964010366 @default.
- W3091706723 cites W2964153729 @default.
- W3091706723 cites W3098155791 @default.
- W3091706723 cites W3122175177 @default.
- W3091706723 hasPublicationYear "2020" @default.
- W3091706723 type Work @default.
- W3091706723 sameAs 3091706723 @default.
- W3091706723 citedByCount "0" @default.
- W3091706723 crossrefType "posted-content" @default.
- W3091706723 hasAuthorship W3091706723A5013049879 @default.
- W3091706723 hasAuthorship W3091706723A5060826513 @default.
- W3091706723 hasAuthorship W3091706723A5080783529 @default.
- W3091706723 hasConcept C105795698 @default.
- W3091706723 hasConcept C119857082 @default.
- W3091706723 hasConcept C126255220 @default.
- W3091706723 hasConcept C137610916 @default.
- W3091706723 hasConcept C147581598 @default.
- W3091706723 hasConcept C154945302 @default.
- W3091706723 hasConcept C207467116 @default.
- W3091706723 hasConcept C2524010 @default.
- W3091706723 hasConcept C2781067378 @default.
- W3091706723 hasConcept C33923547 @default.
- W3091706723 hasConcept C41008148 @default.
- W3091706723 hasConcept C95623464 @default.
- W3091706723 hasConceptScore W3091706723C105795698 @default.
- W3091706723 hasConceptScore W3091706723C119857082 @default.
- W3091706723 hasConceptScore W3091706723C126255220 @default.
- W3091706723 hasConceptScore W3091706723C137610916 @default.
- W3091706723 hasConceptScore W3091706723C147581598 @default.
- W3091706723 hasConceptScore W3091706723C154945302 @default.
- W3091706723 hasConceptScore W3091706723C207467116 @default.
- W3091706723 hasConceptScore W3091706723C2524010 @default.
- W3091706723 hasConceptScore W3091706723C2781067378 @default.
- W3091706723 hasConceptScore W3091706723C33923547 @default.
- W3091706723 hasConceptScore W3091706723C41008148 @default.
- W3091706723 hasConceptScore W3091706723C95623464 @default.
- W3091706723 hasLocation W30917067231 @default.
- W3091706723 hasOpenAccess W3091706723 @default.
- W3091706723 hasPrimaryLocation W30917067231 @default.
- W3091706723 hasRelatedWork W1568733146 @default.
- W3091706723 hasRelatedWork W1661660971 @default.
- W3091706723 hasRelatedWork W1990320099 @default.
- W3091706723 hasRelatedWork W2216589588 @default.
- W3091706723 hasRelatedWork W2234598170 @default.
- W3091706723 hasRelatedWork W2395005906 @default.
- W3091706723 hasRelatedWork W2593813523 @default.
- W3091706723 hasRelatedWork W2753742995 @default.
- W3091706723 hasRelatedWork W2767029637 @default.
- W3091706723 hasRelatedWork W2806772626 @default.
- W3091706723 hasRelatedWork W2881696115 @default.
- W3091706723 hasRelatedWork W3008154176 @default.
- W3091706723 hasRelatedWork W3027956846 @default.
- W3091706723 hasRelatedWork W3033041687 @default.
- W3091706723 hasRelatedWork W3098430511 @default.
- W3091706723 hasRelatedWork W3127125198 @default.
- W3091706723 hasRelatedWork W3129346962 @default.
- W3091706723 hasRelatedWork W3171481457 @default.
- W3091706723 hasRelatedWork W3174677108 @default.
- W3091706723 hasRelatedWork W3210855747 @default.
- W3091706723 isParatext "false" @default.
- W3091706723 isRetracted "false" @default.
- W3091706723 magId "3091706723" @default.
- W3091706723 workType "article" @default.