FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2907656810> ?p ?o ?g. }

• W2907656810 abstract "In many real-world learning scenarios, features are only acquirable at a cost constrained under a budget. In this paper, we propose a novel approach for cost-sensitive feature acquisition at the prediction-time. The suggested method acquires features incrementally based on a context-aware feature-value function. We formulate the problem in the reinforcement learning paradigm, and introduce a reward function based on the utility of each feature. Specifically, MC dropout sampling is used to measure expected variations of the model uncertainty which is used as a feature-value function. Furthermore, we suggest sharing representations between the class predictor and value function estimator networks. The suggested approach is completely online and is readily applicable to stream learning setups. The solution is evaluated on three different datasets including the well-known MNIST dataset as a benchmark as well as two cost-sensitive datasets: Yahoo Learning to Rank and a dataset in the medical domain for diabetes classification. According to the results, the proposed method is able to efficiently acquire features and make accurate predictions." @default.
• W2907656810 created "2019-01-11" @default.
• W2907656810 creator A5017065593 @default.
• W2907656810 creator A5037374629 @default.
• W2907656810 creator A5042420593 @default.
• W2907656810 creator A5078132977 @default.
• W2907656810 creator A5091312650 @default.
• W2907656810 date "2019-01-02" @default.
• W2907656810 modified "2023-09-23" @default.
• W2907656810 title "Opportunistic Learning: Budgeted Cost-Sensitive Learning from Data Streams" @default.
• W2907656810 cites W1519196800 @default.
• W2907656810 cites W1522301498 @default.
• W2907656810 cites W1637749384 @default.
• W2907656810 cites W1661660971 @default.
• W2907656810 cites W1757796397 @default.
• W2907656810 cites W2063978378 @default.
• W2907656810 cites W2069870183 @default.
• W2907656810 cites W2077808043 @default.
• W2907656810 cites W2101474437 @default.
• W2907656810 cites W2108278040 @default.
• W2907656810 cites W2128466927 @default.
• W2907656810 cites W2145339207 @default.
• W2907656810 cites W2150280772 @default.
• W2907656810 cites W2154087390 @default.
• W2907656810 cites W2182356372 @default.
• W2907656810 cites W2183159859 @default.
• W2907656810 cites W2261891975 @default.
• W2907656810 cites W2325933960 @default.
• W2907656810 cites W2515289904 @default.
• W2907656810 cites W2526665672 @default.
• W2907656810 cites W2620172851 @default.
• W2907656810 cites W2626967530 @default.
• W2907656810 cites W2754233948 @default.
• W2907656810 cites W2792899180 @default.
• W2907656810 cites W2884475480 @default.
• W2907656810 cites W2898843400 @default.
• W2907656810 cites W2899771611 @default.
• W2907656810 cites W2949654875 @default.
• W2907656810 cites W2963512709 @default.
• W2907656810 cites W2964059111 @default.
• W2907656810 cites W2964152520 @default.
• W2907656810 cites W2964153729 @default.
• W2907656810 hasPublicationYear "2019" @default.
• W2907656810 type Work @default.
• W2907656810 sameAs 2907656810 @default.
• W2907656810 citedByCount "0" @default.
• W2907656810 crossrefType "posted-content" @default.
• W2907656810 hasAuthorship W2907656810A5017065593 @default.
• W2907656810 hasAuthorship W2907656810A5037374629 @default.
• W2907656810 hasAuthorship W2907656810A5042420593 @default.
• W2907656810 hasAuthorship W2907656810A5078132977 @default.
• W2907656810 hasAuthorship W2907656810A5091312650 @default.
• W2907656810 hasConcept C105795698 @default.
• W2907656810 hasConcept C119857082 @default.
• W2907656810 hasConcept C124101348 @default.
• W2907656810 hasConcept C13280743 @default.
• W2907656810 hasConcept C136389625 @default.
• W2907656810 hasConcept C138885662 @default.
• W2907656810 hasConcept C14036430 @default.
• W2907656810 hasConcept C151730666 @default.
• W2907656810 hasConcept C154945302 @default.
• W2907656810 hasConcept C185429906 @default.
• W2907656810 hasConcept C185798385 @default.
• W2907656810 hasConcept C189430467 @default.
• W2907656810 hasConcept C190502265 @default.
• W2907656810 hasConcept C205649164 @default.
• W2907656810 hasConcept C2776145597 @default.
• W2907656810 hasConcept C2776401178 @default.
• W2907656810 hasConcept C2777212361 @default.
• W2907656810 hasConcept C2779343474 @default.
• W2907656810 hasConcept C33923547 @default.
• W2907656810 hasConcept C41008148 @default.
• W2907656810 hasConcept C41895202 @default.
• W2907656810 hasConcept C50644808 @default.
• W2907656810 hasConcept C59404180 @default.
• W2907656810 hasConcept C78458016 @default.
• W2907656810 hasConcept C86037889 @default.
• W2907656810 hasConcept C86803240 @default.
• W2907656810 hasConcept C97541855 @default.
• W2907656810 hasConceptScore W2907656810C105795698 @default.
• W2907656810 hasConceptScore W2907656810C119857082 @default.
• W2907656810 hasConceptScore W2907656810C124101348 @default.
• W2907656810 hasConceptScore W2907656810C13280743 @default.
• W2907656810 hasConceptScore W2907656810C136389625 @default.
• W2907656810 hasConceptScore W2907656810C138885662 @default.
• W2907656810 hasConceptScore W2907656810C14036430 @default.
• W2907656810 hasConceptScore W2907656810C151730666 @default.
• W2907656810 hasConceptScore W2907656810C154945302 @default.
• W2907656810 hasConceptScore W2907656810C185429906 @default.
• W2907656810 hasConceptScore W2907656810C185798385 @default.
• W2907656810 hasConceptScore W2907656810C189430467 @default.
• W2907656810 hasConceptScore W2907656810C190502265 @default.
• W2907656810 hasConceptScore W2907656810C205649164 @default.
• W2907656810 hasConceptScore W2907656810C2776145597 @default.
• W2907656810 hasConceptScore W2907656810C2776401178 @default.
• W2907656810 hasConceptScore W2907656810C2777212361 @default.
• W2907656810 hasConceptScore W2907656810C2779343474 @default.
• W2907656810 hasConceptScore W2907656810C33923547 @default.
• W2907656810 hasConceptScore W2907656810C41008148 @default.
• W2907656810 hasConceptScore W2907656810C41895202 @default.

• next