FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2593236586> ?p ?o ?g. }

• W2593236586 endingPage "1674" @default.
• W2593236586 startingPage "1665" @default.
• W2593236586 abstract "We consider multi-class classification where the predictor has a hierarchical structure that allows for a very large number of labels both at train and test time. The predictive power of such models can heavily depend on the structure of the tree, and although past work showed how to learn the tree structure, it expected that the feature vectors remained static. We provide a novel algorithm to simultaneously perform representation learning for the input data and learning of the hierarchical predictor. Our approach optimizes an objective function which favors balanced and easily-separable multi-way node partitions. We theoretically analyze this objective, showing that it gives rise to a boosting style property and a bound on classification error. We next show how to extend the algorithm to conditional density estimation. We empirically validate both variants of the algorithm on text classification and language modeling, respectively, and show that they compare favorably to common baselines in terms of accuracy and running time." @default.
• W2593236586 created "2017-03-16" @default.
• W2593236586 creator A5000126238 @default.
• W2593236586 creator A5006452373 @default.
• W2593236586 creator A5013431623 @default.
• W2593236586 date "2017-08-06" @default.
• W2593236586 modified "2023-10-14" @default.
• W2593236586 title "Simultaneous learning of trees and representations for extreme classification and density estimation" @default.
• W2593236586 cites W1558797106 @default.
• W2593236586 cites W1594031697 @default.
• W2593236586 cites W1597533204 @default.
• W2593236586 cites W1692991189 @default.
• W2593236586 cites W179875071 @default.
• W2593236586 cites W1834987204 @default.
• W2593236586 cites W2026160650 @default.
• W2593236586 cites W2034416530 @default.
• W2593236586 cites W2056590938 @default.
• W2593236586 cites W2068074736 @default.
• W2593236586 cites W2077723394 @default.
• W2593236586 cites W20853332 @default.
• W2593236586 cites W2091812280 @default.
• W2593236586 cites W2095181741 @default.
• W2593236586 cites W21006490 @default.
• W2593236586 cites W2103763702 @default.
• W2593236586 cites W2104246439 @default.
• W2593236586 cites W2112846322 @default.
• W2593236586 cites W2113552117 @default.
• W2593236586 cites W2131462252 @default.
• W2593236586 cites W2131494463 @default.
• W2593236586 cites W2132339004 @default.
• W2593236586 cites W2134237567 @default.
• W2593236586 cites W2138204974 @default.
• W2593236586 cites W2150385485 @default.
• W2593236586 cites W2151308547 @default.
• W2593236586 cites W2152808281 @default.
• W2593236586 cites W2155144632 @default.
• W2593236586 cites W2157065343 @default.
• W2593236586 cites W2183087644 @default.
• W2593236586 cites W2185726469 @default.
• W2593236586 cites W2220384803 @default.
• W2593236586 cites W2250384498 @default.
• W2593236586 cites W2250460709 @default.
• W2593236586 cites W2295800168 @default.
• W2593236586 cites W2408114203 @default.
• W2593236586 cites W2423595043 @default.
• W2593236586 cites W2437096199 @default.
• W2593236586 cites W2468328197 @default.
• W2593236586 cites W2519314406 @default.
• W2593236586 cites W2911964244 @default.
• W2593236586 cites W2950133940 @default.
• W2593236586 cites W2951238624 @default.
• W2593236586 cites W2951440817 @default.
• W2593236586 cites W2962876041 @default.
• W2593236586 cites W2963880114 @default.
• W2593236586 cites W36903255 @default.
• W2593236586 hasPublicationYear "2017" @default.
• W2593236586 type Work @default.
• W2593236586 sameAs 2593236586 @default.
• W2593236586 citedByCount "9" @default.
• W2593236586 countsByYear W25932365862018 @default.
• W2593236586 countsByYear W25932365862019 @default.
• W2593236586 countsByYear W25932365862020 @default.
• W2593236586 countsByYear W25932365862021 @default.
• W2593236586 crossrefType "proceedings-article" @default.
• W2593236586 hasAuthorship W2593236586A5000126238 @default.
• W2593236586 hasAuthorship W2593236586A5006452373 @default.
• W2593236586 hasAuthorship W2593236586A5013431623 @default.
• W2593236586 hasConcept C111472728 @default.
• W2593236586 hasConcept C113174947 @default.
• W2593236586 hasConcept C11413529 @default.
• W2593236586 hasConcept C119857082 @default.
• W2593236586 hasConcept C134306372 @default.
• W2593236586 hasConcept C138885662 @default.
• W2593236586 hasConcept C153180895 @default.
• W2593236586 hasConcept C154945302 @default.
• W2593236586 hasConcept C163797641 @default.
• W2593236586 hasConcept C17744445 @default.
• W2593236586 hasConcept C189950617 @default.
• W2593236586 hasConcept C197855036 @default.
• W2593236586 hasConcept C199539241 @default.
• W2593236586 hasConcept C2776359362 @default.
• W2593236586 hasConcept C33923547 @default.
• W2593236586 hasConcept C41008148 @default.
• W2593236586 hasConcept C46686674 @default.
• W2593236586 hasConcept C94625758 @default.
• W2593236586 hasConceptScore W2593236586C111472728 @default.
• W2593236586 hasConceptScore W2593236586C113174947 @default.
• W2593236586 hasConceptScore W2593236586C11413529 @default.
• W2593236586 hasConceptScore W2593236586C119857082 @default.
• W2593236586 hasConceptScore W2593236586C134306372 @default.
• W2593236586 hasConceptScore W2593236586C138885662 @default.
• W2593236586 hasConceptScore W2593236586C153180895 @default.
• W2593236586 hasConceptScore W2593236586C154945302 @default.
• W2593236586 hasConceptScore W2593236586C163797641 @default.
• W2593236586 hasConceptScore W2593236586C17744445 @default.
• W2593236586 hasConceptScore W2593236586C189950617 @default.
• W2593236586 hasConceptScore W2593236586C197855036 @default.
• W2593236586 hasConceptScore W2593236586C199539241 @default.

• next