Matches in SemOpenAlex for { <https://semopenalex.org/work/W2520758021> ?p ?o ?g. }
- W2520758021 endingPage "4433" @default.
- W2520758021 startingPage "4384" @default.
- W2520758021 abstract "We propose a new theoretical framework for analyzing the multiple-instance learning (MIL) setting. In MIL, training examples are provided to a learning algorithm in the form of labeled sets, or bags, of instances. Applications of MIL include 3-D quantitative structure-activity relationship prediction for drug discovery and content-based image retrieval for web search. The goal of an algorithm is to learn a function that correctly labels new bags or a function that correctly labels new instances. We propose that bags should be treated as latent distributions from which samples are observed. We show that it is possible to learn accurate instance - and bag-labeling functions in this setting as well as functions that correctly rank bags or instances under weak assumptions. Additionally, our theoretical results suggest that it is possible to learn to rank efficiently using traditional, well-studied learning approaches. We perform an extensive empirical evaluation that supports the theoretical predictions entailed by the new framework. The proposed theoretical framework leads to a better understanding of the relationship between the MI and standard supervised learning settings, and it provides new methods for learning from MI data that are more accurate, more efficient, and have better understood theoretical properties than existing MI-specific algorithms." @default.
- W2520758021 created "2016-09-23" @default.
- W2520758021 creator A5035284993 @default.
- W2520758021 creator A5055101678 @default.
- W2520758021 date "2016-01-01" @default.
- W2520758021 modified "2023-10-18" @default.
- W2520758021 title "Multiple-instance learning from distributions" @default.
- W2520758021 cites W1535599202 @default.
- W2520758021 cites W1540386283 @default.
- W2520758021 cites W1547172162 @default.
- W2520758021 cites W1548431924 @default.
- W2520758021 cites W1565746575 @default.
- W2520758021 cites W1618905105 @default.
- W2520758021 cites W1661219383 @default.
- W2520758021 cites W1745796331 @default.
- W2520758021 cites W1790119552 @default.
- W2520758021 cites W1880262756 @default.
- W2520758021 cites W1956559956 @default.
- W2520758021 cites W1968934255 @default.
- W2520758021 cites W2020934501 @default.
- W2520758021 cites W2024016194 @default.
- W2520758021 cites W2029538739 @default.
- W2520758021 cites W2050243593 @default.
- W2520758021 cites W2055719721 @default.
- W2520758021 cites W2068484024 @default.
- W2520758021 cites W2084165935 @default.
- W2520758021 cites W2084544490 @default.
- W2520758021 cites W2097998348 @default.
- W2520758021 cites W2098166271 @default.
- W2520758021 cites W2107034620 @default.
- W2520758021 cites W2108745803 @default.
- W2520758021 cites W2110119381 @default.
- W2520758021 cites W2115672776 @default.
- W2520758021 cites W2122105408 @default.
- W2520758021 cites W2128678390 @default.
- W2520758021 cites W2128709346 @default.
- W2520758021 cites W2129192653 @default.
- W2520758021 cites W2130747910 @default.
- W2520758021 cites W2132786922 @default.
- W2520758021 cites W2133288557 @default.
- W2520758021 cites W2134282875 @default.
- W2520758021 cites W2135705692 @default.
- W2520758021 cites W2137917285 @default.
- W2520758021 cites W2144537364 @default.
- W2520758021 cites W2150691697 @default.
- W2520758021 cites W2151134200 @default.
- W2520758021 cites W2154318594 @default.
- W2520758021 cites W2154952480 @default.
- W2520758021 cites W2155392939 @default.
- W2520758021 cites W2157825442 @default.
- W2520758021 cites W2162685317 @default.
- W2520758021 cites W2177692090 @default.
- W2520758021 cites W2222844749 @default.
- W2520758021 cites W2404780394 @default.
- W2520758021 cites W2503956817 @default.
- W2520758021 cites W2523380303 @default.
- W2520758021 cites W2963891219 @default.
- W2520758021 cites W2964324211 @default.
- W2520758021 cites W2984799151 @default.
- W2520758021 cites W3005347330 @default.
- W2520758021 hasPublicationYear "2016" @default.
- W2520758021 type Work @default.
- W2520758021 sameAs 2520758021 @default.
- W2520758021 citedByCount "7" @default.
- W2520758021 countsByYear W25207580212017 @default.
- W2520758021 countsByYear W25207580212018 @default.
- W2520758021 countsByYear W25207580212019 @default.
- W2520758021 countsByYear W25207580212021 @default.
- W2520758021 crossrefType "journal-article" @default.
- W2520758021 hasAuthorship W2520758021A5035284993 @default.
- W2520758021 hasAuthorship W2520758021A5055101678 @default.
- W2520758021 hasConcept C114614502 @default.
- W2520758021 hasConcept C119857082 @default.
- W2520758021 hasConcept C124101348 @default.
- W2520758021 hasConcept C14036430 @default.
- W2520758021 hasConcept C154945302 @default.
- W2520758021 hasConcept C164226766 @default.
- W2520758021 hasConcept C33923547 @default.
- W2520758021 hasConcept C41008148 @default.
- W2520758021 hasConcept C58973888 @default.
- W2520758021 hasConcept C78458016 @default.
- W2520758021 hasConcept C86803240 @default.
- W2520758021 hasConceptScore W2520758021C114614502 @default.
- W2520758021 hasConceptScore W2520758021C119857082 @default.
- W2520758021 hasConceptScore W2520758021C124101348 @default.
- W2520758021 hasConceptScore W2520758021C14036430 @default.
- W2520758021 hasConceptScore W2520758021C154945302 @default.
- W2520758021 hasConceptScore W2520758021C164226766 @default.
- W2520758021 hasConceptScore W2520758021C33923547 @default.
- W2520758021 hasConceptScore W2520758021C41008148 @default.
- W2520758021 hasConceptScore W2520758021C58973888 @default.
- W2520758021 hasConceptScore W2520758021C78458016 @default.
- W2520758021 hasConceptScore W2520758021C86803240 @default.
- W2520758021 hasIssue "1" @default.
- W2520758021 hasLocation W25207580211 @default.
- W2520758021 hasOpenAccess W2520758021 @default.
- W2520758021 hasPrimaryLocation W25207580211 @default.
- W2520758021 hasRelatedWork W1492130155 @default.