Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035009331> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W3035009331 endingPage "9469" @default.
- W3035009331 startingPage "9458" @default.
- W3035009331 abstract "We study few-shot supervised domain adaptation (DA) for regression problems, where only a few labeled target domain data and many labeled source domain data are available. Many of the current DA methods base their transfer assumptions on either parametrized distribution shift or apparent distribution similarities, e.g., identical conditionals or small distributional discrepancies. However, these assumptions may preclude the possibility of adaptation from intricately shifted and apparently very different distributions. To overcome this problem, we propose mechanism transfer, a meta-distributional scenario in which a data generating mechanism is invariant among domains. This transfer assumption can accommodate nonparametric shifts resulting in apparently different distributions while providing a solid statistical basis for DA. We take the structural equations in causal modeling as an example and propose a novel DA method, which is shown to be useful both theoretically and experimentally. Our method can be seen as the first attempt to fully leverage the structural causal models for DA." @default.
- W3035009331 created "2020-06-19" @default.
- W3035009331 creator A5051177899 @default.
- W3035009331 creator A5060421432 @default.
- W3035009331 creator A5072744508 @default.
- W3035009331 date "2020-07-12" @default.
- W3035009331 modified "2023-10-01" @default.
- W3035009331 title "Few-shot Domain Adaptation by Causal Mechanism Transfer" @default.
- W3035009331 hasPublicationYear "2020" @default.
- W3035009331 type Work @default.
- W3035009331 sameAs 3035009331 @default.
- W3035009331 citedByCount "12" @default.
- W3035009331 countsByYear W30350093312020 @default.
- W3035009331 countsByYear W30350093312021 @default.
- W3035009331 countsByYear W30350093312022 @default.
- W3035009331 crossrefType "proceedings-article" @default.
- W3035009331 hasAuthorship W3035009331A5051177899 @default.
- W3035009331 hasAuthorship W3035009331A5060421432 @default.
- W3035009331 hasAuthorship W3035009331A5072744508 @default.
- W3035009331 hasConcept C102366305 @default.
- W3035009331 hasConcept C111472728 @default.
- W3035009331 hasConcept C134306372 @default.
- W3035009331 hasConcept C138885662 @default.
- W3035009331 hasConcept C149782125 @default.
- W3035009331 hasConcept C150899416 @default.
- W3035009331 hasConcept C153083717 @default.
- W3035009331 hasConcept C154945302 @default.
- W3035009331 hasConcept C2776434776 @default.
- W3035009331 hasConcept C33923547 @default.
- W3035009331 hasConcept C36503486 @default.
- W3035009331 hasConcept C41008148 @default.
- W3035009331 hasConcept C89611455 @default.
- W3035009331 hasConcept C95623464 @default.
- W3035009331 hasConceptScore W3035009331C102366305 @default.
- W3035009331 hasConceptScore W3035009331C111472728 @default.
- W3035009331 hasConceptScore W3035009331C134306372 @default.
- W3035009331 hasConceptScore W3035009331C138885662 @default.
- W3035009331 hasConceptScore W3035009331C149782125 @default.
- W3035009331 hasConceptScore W3035009331C150899416 @default.
- W3035009331 hasConceptScore W3035009331C153083717 @default.
- W3035009331 hasConceptScore W3035009331C154945302 @default.
- W3035009331 hasConceptScore W3035009331C2776434776 @default.
- W3035009331 hasConceptScore W3035009331C33923547 @default.
- W3035009331 hasConceptScore W3035009331C36503486 @default.
- W3035009331 hasConceptScore W3035009331C41008148 @default.
- W3035009331 hasConceptScore W3035009331C89611455 @default.
- W3035009331 hasConceptScore W3035009331C95623464 @default.
- W3035009331 hasLocation W30350093311 @default.
- W3035009331 hasOpenAccess W3035009331 @default.
- W3035009331 hasPrimaryLocation W30350093311 @default.
- W3035009331 hasRelatedWork W1482778976 @default.
- W3035009331 hasRelatedWork W2010816667 @default.
- W3035009331 hasRelatedWork W2070922554 @default.
- W3035009331 hasRelatedWork W2182035674 @default.
- W3035009331 hasRelatedWork W2194775991 @default.
- W3035009331 hasRelatedWork W2291171832 @default.
- W3035009331 hasRelatedWork W2528074386 @default.
- W3035009331 hasRelatedWork W2785125662 @default.
- W3035009331 hasRelatedWork W28922975 @default.
- W3035009331 hasRelatedWork W2950751349 @default.
- W3035009331 hasRelatedWork W2952708040 @default.
- W3035009331 hasRelatedWork W2975249723 @default.
- W3035009331 hasRelatedWork W3005304986 @default.
- W3035009331 hasRelatedWork W3047695914 @default.
- W3035009331 hasRelatedWork W3049219621 @default.
- W3035009331 hasRelatedWork W3093313184 @default.
- W3035009331 hasRelatedWork W3098520424 @default.
- W3035009331 hasRelatedWork W3106137229 @default.
- W3035009331 hasRelatedWork W3147972065 @default.
- W3035009331 hasRelatedWork W2463971374 @default.
- W3035009331 hasVolume "1" @default.
- W3035009331 isParatext "false" @default.
- W3035009331 isRetracted "false" @default.
- W3035009331 magId "3035009331" @default.
- W3035009331 workType "article" @default.