FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2404232502> ?p ?o ?g. }

• W2404232502 abstract "Active learning is a machine learning technique that trains a classifier after selecting a subset from an unlabeled dataset for labeling and using the selected data for training. Recently, batch mode active learning, which selects a batch of samples to label in parallel, has attracted a lot of attention. Its challenge lies in the choice of criteria used for guiding the search of the optimal batch. In this paper, we propose a novel approach to selecting the optimal batch of queries by minimizing the α-relative Pearson divergence (RPE) between the labeled and the original datasets. This particular divergence is chosen since it can distinguish the optimal batch more easily than other measures especially when available candidates are similar. The proposed objective is a min-max optimization problem, and it is difficult to solve due to the involvement of both minimization and maximization. We find that the objective has an equivalent convex form, and thus a global optimal solution can be obtained. Then the subgradient method can be applied to solve the simplified convex problem. Our empirical studies on UCI datasets demonstrate the effectiveness of the proposed approach compared with the state-of-the-art batch mode active learning methods." @default.
• W2404232502 created "2016-06-24" @default.
• W2404232502 creator A5004080941 @default.
• W2404232502 creator A5016197750 @default.
• W2404232502 creator A5018193643 @default.
• W2404232502 creator A5029205297 @default.
• W2404232502 creator A5051466085 @default.
• W2404232502 date "2015-02-21" @default.
• W2404232502 modified "2023-09-27" @default.
• W2404232502 title "Convex Batch Mode Active Sampling via α-Relative Pearson Divergence" @default.
• W2404232502 cites W1483816357 @default.
• W2404232502 cites W1514940655 @default.
• W2404232502 cites W1528361845 @default.
• W2404232502 cites W1553262910 @default.
• W2404232502 cites W1965555277 @default.
• W2404232502 cites W1985077192 @default.
• W2404232502 cites W1991234467 @default.
• W2404232502 cites W2080021732 @default.
• W2404232502 cites W2101895600 @default.
• W2404232502 cites W2104848109 @default.
• W2404232502 cites W2114188922 @default.
• W2404232502 cites W2125865219 @default.
• W2404232502 cites W2132948751 @default.
• W2404232502 cites W2137795521 @default.
• W2404232502 cites W2160086716 @default.
• W2404232502 cites W2171671120 @default.
• W2404232502 cites W2296319761 @default.
• W2404232502 cites W2426031434 @default.
• W2404232502 cites W2735257517 @default.
• W2404232502 cites W2752885492 @default.
• W2404232502 cites W2903158431 @default.
• W2404232502 doi "https://doi.org/10.1609/aaai.v29i1.9618" @default.
• W2404232502 hasPublicationYear "2015" @default.
• W2404232502 type Work @default.
• W2404232502 sameAs 2404232502 @default.
• W2404232502 citedByCount "5" @default.
• W2404232502 countsByYear W24042325022018 @default.
• W2404232502 countsByYear W24042325022020 @default.
• W2404232502 countsByYear W24042325022022 @default.
• W2404232502 crossrefType "journal-article" @default.
• W2404232502 hasAuthorship W2404232502A5004080941 @default.
• W2404232502 hasAuthorship W2404232502A5016197750 @default.
• W2404232502 hasAuthorship W2404232502A5018193643 @default.
• W2404232502 hasAuthorship W2404232502A5029205297 @default.
• W2404232502 hasAuthorship W2404232502A5051466085 @default.
• W2404232502 hasBestOaLocation W24042325021 @default.
• W2404232502 hasConcept C112680207 @default.
• W2404232502 hasConcept C119857082 @default.
• W2404232502 hasConcept C126255220 @default.
• W2404232502 hasConcept C138885662 @default.
• W2404232502 hasConcept C147764199 @default.
• W2404232502 hasConcept C154945302 @default.
• W2404232502 hasConcept C157972887 @default.
• W2404232502 hasConcept C158968445 @default.
• W2404232502 hasConcept C171752962 @default.
• W2404232502 hasConcept C172658912 @default.
• W2404232502 hasConcept C199360897 @default.
• W2404232502 hasConcept C207390915 @default.
• W2404232502 hasConcept C2524010 @default.
• W2404232502 hasConcept C2776330181 @default.
• W2404232502 hasConcept C33923547 @default.
• W2404232502 hasConcept C41008148 @default.
• W2404232502 hasConcept C41895202 @default.
• W2404232502 hasConcept C95623464 @default.
• W2404232502 hasConceptScore W2404232502C112680207 @default.
• W2404232502 hasConceptScore W2404232502C119857082 @default.
• W2404232502 hasConceptScore W2404232502C126255220 @default.
• W2404232502 hasConceptScore W2404232502C138885662 @default.
• W2404232502 hasConceptScore W2404232502C147764199 @default.
• W2404232502 hasConceptScore W2404232502C154945302 @default.
• W2404232502 hasConceptScore W2404232502C157972887 @default.
• W2404232502 hasConceptScore W2404232502C158968445 @default.
• W2404232502 hasConceptScore W2404232502C171752962 @default.
• W2404232502 hasConceptScore W2404232502C172658912 @default.
• W2404232502 hasConceptScore W2404232502C199360897 @default.
• W2404232502 hasConceptScore W2404232502C207390915 @default.
• W2404232502 hasConceptScore W2404232502C2524010 @default.
• W2404232502 hasConceptScore W2404232502C2776330181 @default.
• W2404232502 hasConceptScore W2404232502C33923547 @default.
• W2404232502 hasConceptScore W2404232502C41008148 @default.
• W2404232502 hasConceptScore W2404232502C41895202 @default.
• W2404232502 hasConceptScore W2404232502C95623464 @default.
• W2404232502 hasIssue "1" @default.
• W2404232502 hasLocation W24042325021 @default.
• W2404232502 hasOpenAccess W2404232502 @default.
• W2404232502 hasPrimaryLocation W24042325021 @default.
• W2404232502 hasRelatedWork W2079688774 @default.
• W2404232502 hasRelatedWork W2083145615 @default.
• W2404232502 hasRelatedWork W2150706587 @default.
• W2404232502 hasRelatedWork W2153631186 @default.
• W2404232502 hasRelatedWork W2338763366 @default.
• W2404232502 hasRelatedWork W2404232502 @default.
• W2404232502 hasRelatedWork W2568948068 @default.
• W2404232502 hasRelatedWork W2950826412 @default.
• W2404232502 hasRelatedWork W2973078793 @default.
• W2404232502 hasRelatedWork W3090464062 @default.
• W2404232502 hasVolume "29" @default.
• W2404232502 isParatext "false" @default.
• W2404232502 isRetracted "false" @default.
• W2404232502 magId "2404232502" @default.

• next