Matches in SemOpenAlex for { <https://semopenalex.org/work/W3166158595> ?p ?o ?g. }
- W3166158595 abstract "Can we learn a multi-class classifier from only data of a single class? We show that without any assumptions on the loss functions, models, and optimizers, we can successfully learn a multi-class classifier from only data of a single class with a rigorous consistency guarantee when confidences (i.e., the class-posterior probabilities for all the classes) are available. Specifically, we propose an empirical risk minimization framework that is loss-/model-/optimizer-independent. Instead of constructing a boundary between the given class and other classes, our method can conduct discriminative classification between all the classes even if no data from the other classes are provided. We further theoretically and experimentally show that our method can be Bayes-consistent with a simple modification even if the provided confidences are highly noisy. Then, we provide an extension of our method for the case where data from a subset of all the classes are available. Experimental results demonstrate the effectiveness of our methods." @default.
- W3166158595 created "2021-06-22" @default.
- W3166158595 creator A5005702106 @default.
- W3166158595 creator A5007098537 @default.
- W3166158595 creator A5017743551 @default.
- W3166158595 creator A5039818538 @default.
- W3166158595 creator A5040537076 @default.
- W3166158595 creator A5056213361 @default.
- W3166158595 creator A5072744508 @default.
- W3166158595 date "2021-06-16" @default.
- W3166158595 modified "2023-09-23" @default.
- W3166158595 title "Multi-Class Classification from Single-Class Data with Confidences." @default.
- W3166158595 cites W1479807131 @default.
- W3166158595 cites W1480538416 @default.
- W3166158595 cites W1825821140 @default.
- W3166158595 cites W1990334093 @default.
- W3166158595 cites W2019288156 @default.
- W3166158595 cites W2095838485 @default.
- W3166158595 cites W2096520669 @default.
- W3166158595 cites W2096706838 @default.
- W3166158595 cites W2100294832 @default.
- W3166158595 cites W2101234009 @default.
- W3166158595 cites W2112796928 @default.
- W3166158595 cites W2113290770 @default.
- W3166158595 cites W2123958887 @default.
- W3166158595 cites W2132442585 @default.
- W3166158595 cites W2132870739 @default.
- W3166158595 cites W2144182447 @default.
- W3166158595 cites W2158681777 @default.
- W3166158595 cites W2194775991 @default.
- W3166158595 cites W2507587187 @default.
- W3166158595 cites W2579923771 @default.
- W3166158595 cites W2742033716 @default.
- W3166158595 cites W2746791238 @default.
- W3166158595 cites W2803697594 @default.
- W3166158595 cites W2913691358 @default.
- W3166158595 cites W2943766732 @default.
- W3166158595 cites W2951094201 @default.
- W3166158595 cites W2962708723 @default.
- W3166158595 cites W2962971234 @default.
- W3166158595 cites W2963091836 @default.
- W3166158595 cites W2963335560 @default.
- W3166158595 cites W2963446712 @default.
- W3166158595 cites W2963473212 @default.
- W3166158595 cites W2963644303 @default.
- W3166158595 cites W2963735582 @default.
- W3166158595 cites W2963909971 @default.
- W3166158595 cites W2964083560 @default.
- W3166158595 cites W2964121744 @default.
- W3166158595 cites W2970971581 @default.
- W3166158595 cites W2989661724 @default.
- W3166158595 cites W3034332915 @default.
- W3166158595 cites W3034763255 @default.
- W3166158595 cites W3035019293 @default.
- W3166158595 cites W3035370681 @default.
- W3166158595 cites W3037723470 @default.
- W3166158595 cites W3081467912 @default.
- W3166158595 cites W3101114756 @default.
- W3166158595 cites W3107397683 @default.
- W3166158595 cites W3118608800 @default.
- W3166158595 cites W3119586787 @default.
- W3166158595 cites W3129874696 @default.
- W3166158595 cites W91088564 @default.
- W3166158595 hasPublicationYear "2021" @default.
- W3166158595 type Work @default.
- W3166158595 sameAs 3166158595 @default.
- W3166158595 citedByCount "0" @default.
- W3166158595 crossrefType "posted-content" @default.
- W3166158595 hasAuthorship W3166158595A5005702106 @default.
- W3166158595 hasAuthorship W3166158595A5007098537 @default.
- W3166158595 hasAuthorship W3166158595A5017743551 @default.
- W3166158595 hasAuthorship W3166158595A5039818538 @default.
- W3166158595 hasAuthorship W3166158595A5040537076 @default.
- W3166158595 hasAuthorship W3166158595A5056213361 @default.
- W3166158595 hasAuthorship W3166158595A5072744508 @default.
- W3166158595 hasConcept C119857082 @default.
- W3166158595 hasConcept C12267149 @default.
- W3166158595 hasConcept C124101348 @default.
- W3166158595 hasConcept C153180895 @default.
- W3166158595 hasConcept C154945302 @default.
- W3166158595 hasConcept C2777212361 @default.
- W3166158595 hasConcept C33923547 @default.
- W3166158595 hasConcept C41008148 @default.
- W3166158595 hasConcept C52001869 @default.
- W3166158595 hasConcept C95623464 @default.
- W3166158595 hasConcept C97931131 @default.
- W3166158595 hasConceptScore W3166158595C119857082 @default.
- W3166158595 hasConceptScore W3166158595C12267149 @default.
- W3166158595 hasConceptScore W3166158595C124101348 @default.
- W3166158595 hasConceptScore W3166158595C153180895 @default.
- W3166158595 hasConceptScore W3166158595C154945302 @default.
- W3166158595 hasConceptScore W3166158595C2777212361 @default.
- W3166158595 hasConceptScore W3166158595C33923547 @default.
- W3166158595 hasConceptScore W3166158595C41008148 @default.
- W3166158595 hasConceptScore W3166158595C52001869 @default.
- W3166158595 hasConceptScore W3166158595C95623464 @default.
- W3166158595 hasConceptScore W3166158595C97931131 @default.
- W3166158595 hasLocation W31661585951 @default.
- W3166158595 hasOpenAccess W3166158595 @default.
- W3166158595 hasPrimaryLocation W31661585951 @default.