Matches in SemOpenAlex for { <https://semopenalex.org/work/W2971192944> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W2971192944 abstract "When end users apply a machine learning (ML) model on new unlabeled data, it is difficult for them to decide whether they can trust its predictions. Errors or shifts in the target data can lead to hard-to-detect drops in the predictive quality of the model. We therefore propose an approach to assist non-ML experts working with pretrained ML models. Our approach estimates the change in prediction performance of a model on unseen target data. It does not require explicit distributional assumptions on the dataset shift between the training and target data. Instead, a domain expert can declaratively specify typical cases of dataset shift that she expects to observe in real-world data. Based on this information, we learn a performance predictor for pretrained black box models, which can be combined with the model, and automatically warns end users in case of unexpected performance drops. We demonstrate the effectiveness of our approach on two models -- logistic regression and a neural network, applied to several real-world datasets." @default.
- W2971192944 created "2019-09-05" @default.
- W2971192944 creator A5002413906 @default.
- W2971192944 creator A5024953386 @default.
- W2971192944 creator A5027386823 @default.
- W2971192944 creator A5028425403 @default.
- W2971192944 creator A5033843672 @default.
- W2971192944 date "2019-07-05" @default.
- W2971192944 modified "2023-10-03" @default.
- W2971192944 title "Learning to Validate the Predictions of Black Box Machine Learning Models on Unseen Data" @default.
- W2971192944 cites W2743948853 @default.
- W2971192944 cites W2889249015 @default.
- W2971192944 doi "https://doi.org/10.1145/3328519.3329126" @default.
- W2971192944 hasPublicationYear "2019" @default.
- W2971192944 type Work @default.
- W2971192944 sameAs 2971192944 @default.
- W2971192944 citedByCount "4" @default.
- W2971192944 countsByYear W29711929442020 @default.
- W2971192944 countsByYear W29711929442021 @default.
- W2971192944 countsByYear W29711929442022 @default.
- W2971192944 crossrefType "proceedings-article" @default.
- W2971192944 hasAuthorship W2971192944A5002413906 @default.
- W2971192944 hasAuthorship W2971192944A5024953386 @default.
- W2971192944 hasAuthorship W2971192944A5027386823 @default.
- W2971192944 hasAuthorship W2971192944A5028425403 @default.
- W2971192944 hasAuthorship W2971192944A5033843672 @default.
- W2971192944 hasConcept C111472728 @default.
- W2971192944 hasConcept C119857082 @default.
- W2971192944 hasConcept C124101348 @default.
- W2971192944 hasConcept C134306372 @default.
- W2971192944 hasConcept C138885662 @default.
- W2971192944 hasConcept C154945302 @default.
- W2971192944 hasConcept C2779530757 @default.
- W2971192944 hasConcept C33923547 @default.
- W2971192944 hasConcept C36503486 @default.
- W2971192944 hasConcept C41008148 @default.
- W2971192944 hasConcept C50644808 @default.
- W2971192944 hasConcept C51632099 @default.
- W2971192944 hasConcept C67186912 @default.
- W2971192944 hasConcept C77088390 @default.
- W2971192944 hasConcept C94966114 @default.
- W2971192944 hasConceptScore W2971192944C111472728 @default.
- W2971192944 hasConceptScore W2971192944C119857082 @default.
- W2971192944 hasConceptScore W2971192944C124101348 @default.
- W2971192944 hasConceptScore W2971192944C134306372 @default.
- W2971192944 hasConceptScore W2971192944C138885662 @default.
- W2971192944 hasConceptScore W2971192944C154945302 @default.
- W2971192944 hasConceptScore W2971192944C2779530757 @default.
- W2971192944 hasConceptScore W2971192944C33923547 @default.
- W2971192944 hasConceptScore W2971192944C36503486 @default.
- W2971192944 hasConceptScore W2971192944C41008148 @default.
- W2971192944 hasConceptScore W2971192944C50644808 @default.
- W2971192944 hasConceptScore W2971192944C51632099 @default.
- W2971192944 hasConceptScore W2971192944C67186912 @default.
- W2971192944 hasConceptScore W2971192944C77088390 @default.
- W2971192944 hasConceptScore W2971192944C94966114 @default.
- W2971192944 hasFunder F4320306202 @default.
- W2971192944 hasLocation W29711929441 @default.
- W2971192944 hasOpenAccess W2971192944 @default.
- W2971192944 hasPrimaryLocation W29711929441 @default.
- W2971192944 hasRelatedWork W1971605519 @default.
- W2971192944 hasRelatedWork W2122552724 @default.
- W2971192944 hasRelatedWork W2350386639 @default.
- W2971192944 hasRelatedWork W2360523936 @default.
- W2971192944 hasRelatedWork W2889705046 @default.
- W2971192944 hasRelatedWork W3029990846 @default.
- W2971192944 hasRelatedWork W3193799803 @default.
- W2971192944 hasRelatedWork W3211188136 @default.
- W2971192944 hasRelatedWork W4213225422 @default.
- W2971192944 hasRelatedWork W1629725936 @default.
- W2971192944 isParatext "false" @default.
- W2971192944 isRetracted "false" @default.
- W2971192944 magId "2971192944" @default.
- W2971192944 workType "article" @default.