Matches in SemOpenAlex for { <https://semopenalex.org/work/W2883672997> ?p ?o ?g. }
- W2883672997 abstract "Label aggregation is an efficient and low cost way to make large datasets for supervised learning. It takes the noisy labels provided by non-experts and infers the unknown true labels. In this paper, we propose a novel label aggregation algorithm which includes a label aggregation neural network. The learning task in this paper is unsupervised. In order to train the neural network, we try to design a suitable guiding model to define the loss function. The optimization goal of our algorithm is to find the consensus between the predictions of the neural network and the guiding model. This algorithm is easy to optimize using mini-batch stochastic optimization methods. Since the choices of the neural network and the guiding model are very flexible, our label aggregation algorithm is easy to extend. According to the algorithm framework, we design two novel models to aggregate noisy labels. Experimental results show that our models achieve better results than state-of-the-art label aggregation methods." @default.
- W2883672997 created "2018-08-03" @default.
- W2883672997 creator A5000610648 @default.
- W2883672997 creator A5070094794 @default.
- W2883672997 date "2018-07-19" @default.
- W2883672997 modified "2023-09-24" @default.
- W2883672997 title "Label Aggregation via Finding Consensus Between Models" @default.
- W2883672997 cites W1459599406 @default.
- W2883672997 cites W1511986666 @default.
- W2883672997 cites W1522301498 @default.
- W2883672997 cites W1663973292 @default.
- W2883672997 cites W1761109129 @default.
- W2883672997 cites W1970381522 @default.
- W2883672997 cites W2055733113 @default.
- W2883672997 cites W2098865355 @default.
- W2883672997 cites W2115394472 @default.
- W2883672997 cites W2120340025 @default.
- W2883672997 cites W2128475742 @default.
- W2883672997 cites W2129345386 @default.
- W2883672997 cites W2134305421 @default.
- W2883672997 cites W2141649520 @default.
- W2883672997 cites W2142518823 @default.
- W2883672997 cites W2148825261 @default.
- W2883672997 cites W2149273804 @default.
- W2883672997 cites W2152009989 @default.
- W2883672997 cites W2187444452 @default.
- W2883672997 cites W2250734828 @default.
- W2883672997 cites W2571859924 @default.
- W2883672997 cites W2739753637 @default.
- W2883672997 cites W2796095752 @default.
- W2883672997 cites W2913790076 @default.
- W2883672997 cites W2945436856 @default.
- W2883672997 cites W2951004968 @default.
- W2883672997 cites W2951395930 @default.
- W2883672997 cites W2951493172 @default.
- W2883672997 cites W2969133367 @default.
- W2883672997 cites W3101504385 @default.
- W2883672997 cites W9014458 @default.
- W2883672997 cites W2461427108 @default.
- W2883672997 hasPublicationYear "2018" @default.
- W2883672997 type Work @default.
- W2883672997 sameAs 2883672997 @default.
- W2883672997 citedByCount "0" @default.
- W2883672997 crossrefType "posted-content" @default.
- W2883672997 hasAuthorship W2883672997A5000610648 @default.
- W2883672997 hasAuthorship W2883672997A5070094794 @default.
- W2883672997 hasConcept C11413529 @default.
- W2883672997 hasConcept C119857082 @default.
- W2883672997 hasConcept C127413603 @default.
- W2883672997 hasConcept C14036430 @default.
- W2883672997 hasConcept C154945302 @default.
- W2883672997 hasConcept C159985019 @default.
- W2883672997 hasConcept C192562407 @default.
- W2883672997 hasConcept C201995342 @default.
- W2883672997 hasConcept C2780451532 @default.
- W2883672997 hasConcept C41008148 @default.
- W2883672997 hasConcept C4679612 @default.
- W2883672997 hasConcept C48103436 @default.
- W2883672997 hasConcept C50644808 @default.
- W2883672997 hasConcept C78458016 @default.
- W2883672997 hasConcept C86803240 @default.
- W2883672997 hasConceptScore W2883672997C11413529 @default.
- W2883672997 hasConceptScore W2883672997C119857082 @default.
- W2883672997 hasConceptScore W2883672997C127413603 @default.
- W2883672997 hasConceptScore W2883672997C14036430 @default.
- W2883672997 hasConceptScore W2883672997C154945302 @default.
- W2883672997 hasConceptScore W2883672997C159985019 @default.
- W2883672997 hasConceptScore W2883672997C192562407 @default.
- W2883672997 hasConceptScore W2883672997C201995342 @default.
- W2883672997 hasConceptScore W2883672997C2780451532 @default.
- W2883672997 hasConceptScore W2883672997C41008148 @default.
- W2883672997 hasConceptScore W2883672997C4679612 @default.
- W2883672997 hasConceptScore W2883672997C48103436 @default.
- W2883672997 hasConceptScore W2883672997C50644808 @default.
- W2883672997 hasConceptScore W2883672997C78458016 @default.
- W2883672997 hasConceptScore W2883672997C86803240 @default.
- W2883672997 hasLocation W28836729971 @default.
- W2883672997 hasOpenAccess W2883672997 @default.
- W2883672997 hasPrimaryLocation W28836729971 @default.
- W2883672997 hasRelatedWork W1996462768 @default.
- W2883672997 hasRelatedWork W2055284675 @default.
- W2883672997 hasRelatedWork W2164682059 @default.
- W2883672997 hasRelatedWork W2191800066 @default.
- W2883672997 hasRelatedWork W2239675528 @default.
- W2883672997 hasRelatedWork W2331805790 @default.
- W2883672997 hasRelatedWork W2360008344 @default.
- W2883672997 hasRelatedWork W2611052687 @default.
- W2883672997 hasRelatedWork W2751120573 @default.
- W2883672997 hasRelatedWork W2760539063 @default.
- W2883672997 hasRelatedWork W2897272669 @default.
- W2883672997 hasRelatedWork W2905479596 @default.
- W2883672997 hasRelatedWork W2908572541 @default.
- W2883672997 hasRelatedWork W2951829787 @default.
- W2883672997 hasRelatedWork W2971297210 @default.
- W2883672997 hasRelatedWork W3035537459 @default.
- W2883672997 hasRelatedWork W3088109833 @default.
- W2883672997 hasRelatedWork W3107258090 @default.
- W2883672997 hasRelatedWork W3196741022 @default.
- W2883672997 hasRelatedWork W3213358055 @default.
- W2883672997 isParatext "false" @default.