Matches in SemOpenAlex for { <https://semopenalex.org/work/W2991356716> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W2991356716 abstract "Methods of transfer learning try to combine knowledge from several related tasks (or domains) to improve performance on a test task. Inspired by causal methodology, we relax the usual covariate shift assumption and assume that it holds true for a subset of predictor variables: the conditional distribution of the target variable given this subset of predictors is invariant over all tasks. We show how this assumption can be motivated from ideas in the field of causality. We focus on the problem of Domain Generalization, in which no examples from the test task are observed. We prove that in an adversarial setting using this subset for prediction is optimal in Domain Generalization; we further provide examples, in which the tasks are sufficiently diverse and the estimator therefore outperforms pooling the data, even on average. If examples from the test task are available, we also provide a method to transfer knowledge from the training tasks and exploit all available features for prediction. However, we provide no guarantees for this method. We introduce a practical method which allows for automatic inference of the above subset and provide corresponding code. We present results on synthetic data sets and a gene deletion data set." @default.
- W2991356716 created "2019-12-05" @default.
- W2991356716 creator A5002127148 @default.
- W2991356716 creator A5044005697 @default.
- W2991356716 creator A5072490106 @default.
- W2991356716 creator A5089280179 @default.
- W2991356716 date "2015-07-19" @default.
- W2991356716 modified "2023-09-27" @default.
- W2991356716 title "A Causal Perspective on Domain Adaptation" @default.
- W2991356716 hasPublicationYear "2015" @default.
- W2991356716 type Work @default.
- W2991356716 sameAs 2991356716 @default.
- W2991356716 citedByCount "1" @default.
- W2991356716 countsByYear W29913567162018 @default.
- W2991356716 crossrefType "posted-content" @default.
- W2991356716 hasAuthorship W2991356716A5002127148 @default.
- W2991356716 hasAuthorship W2991356716A5044005697 @default.
- W2991356716 hasAuthorship W2991356716A5072490106 @default.
- W2991356716 hasAuthorship W2991356716A5089280179 @default.
- W2991356716 hasConcept C105795698 @default.
- W2991356716 hasConcept C119857082 @default.
- W2991356716 hasConcept C12713177 @default.
- W2991356716 hasConcept C134306372 @default.
- W2991356716 hasConcept C149782125 @default.
- W2991356716 hasConcept C154945302 @default.
- W2991356716 hasConcept C158600405 @default.
- W2991356716 hasConcept C165696696 @default.
- W2991356716 hasConcept C177148314 @default.
- W2991356716 hasConcept C185429906 @default.
- W2991356716 hasConcept C2776214188 @default.
- W2991356716 hasConcept C33923547 @default.
- W2991356716 hasConcept C36503486 @default.
- W2991356716 hasConcept C38652104 @default.
- W2991356716 hasConcept C41008148 @default.
- W2991356716 hasConcept C80444323 @default.
- W2991356716 hasConceptScore W2991356716C105795698 @default.
- W2991356716 hasConceptScore W2991356716C119857082 @default.
- W2991356716 hasConceptScore W2991356716C12713177 @default.
- W2991356716 hasConceptScore W2991356716C134306372 @default.
- W2991356716 hasConceptScore W2991356716C149782125 @default.
- W2991356716 hasConceptScore W2991356716C154945302 @default.
- W2991356716 hasConceptScore W2991356716C158600405 @default.
- W2991356716 hasConceptScore W2991356716C165696696 @default.
- W2991356716 hasConceptScore W2991356716C177148314 @default.
- W2991356716 hasConceptScore W2991356716C185429906 @default.
- W2991356716 hasConceptScore W2991356716C2776214188 @default.
- W2991356716 hasConceptScore W2991356716C33923547 @default.
- W2991356716 hasConceptScore W2991356716C36503486 @default.
- W2991356716 hasConceptScore W2991356716C38652104 @default.
- W2991356716 hasConceptScore W2991356716C41008148 @default.
- W2991356716 hasConceptScore W2991356716C80444323 @default.
- W2991356716 hasLocation W29913567161 @default.
- W2991356716 hasOpenAccess W2991356716 @default.
- W2991356716 hasPrimaryLocation W29913567161 @default.
- W2991356716 hasRelatedWork W1665715489 @default.
- W2991356716 hasRelatedWork W2168834831 @default.
- W2991356716 hasRelatedWork W2577778365 @default.
- W2991356716 hasRelatedWork W2891765548 @default.
- W2991356716 hasRelatedWork W2907380995 @default.
- W2991356716 hasRelatedWork W2945670796 @default.
- W2991356716 hasRelatedWork W2951357534 @default.
- W2991356716 hasRelatedWork W2991104793 @default.
- W2991356716 hasRelatedWork W3035752139 @default.
- W2991356716 hasRelatedWork W3036698084 @default.
- W2991356716 hasRelatedWork W3039431315 @default.
- W2991356716 hasRelatedWork W3092170595 @default.
- W2991356716 hasRelatedWork W3133211101 @default.
- W2991356716 hasRelatedWork W3135119215 @default.
- W2991356716 hasRelatedWork W3158155324 @default.
- W2991356716 hasRelatedWork W3198407848 @default.
- W2991356716 hasRelatedWork W3200466256 @default.
- W2991356716 hasRelatedWork W3206193845 @default.
- W2991356716 hasRelatedWork W3212885056 @default.
- W2991356716 hasRelatedWork W3213482536 @default.
- W2991356716 isParatext "false" @default.
- W2991356716 isRetracted "false" @default.
- W2991356716 magId "2991356716" @default.
- W2991356716 workType "article" @default.