Matches in SemOpenAlex for { <https://semopenalex.org/work/W3030662011> ?p ?o ?g. }
- W3030662011 endingPage "151" @default.
- W3030662011 startingPage "140" @default.
- W3030662011 abstract "Abstract We propose a transfer metric learning method to infer domain-specific data embeddings for unseen domains, from which no data are given in the training phase, by using knowledge transferred from related domains. When training and test distributions are different, the standard metric learning cannot infer appropriate data embeddings. The proposed method can infer appropriate data embeddings for the unseen domains by using latent domain vectors, which are latent representations of domains and control the property of data embeddings for each domain. This latent domain vector is inferred by using a neural network that takes the set of feature vectors in the domain as an input. The neural network is trained without the unseen domains. The proposed method can instantly infer data embeddings for the unseen domains without (re)-training once the sets of feature vectors in the domains are given. To accumulate knowledge in advance, the proposed method uses labeled and unlabeled data in multiple source domains. Labeled data, i.e., data with label information such as class labels or pair (similar/dissimilar) constraints, are used for learning data embeddings in such a way that similar data points are close and dissimilar data points are separated in the embedding space. Although unlabeled data do not have labels, they have geometric information that characterizes domains. The proposed method incorporates this information in a natural way on the basis of a probabilistic framework. The conditional distributions of the latent domain vectors, the embedded data, and the observed data are parameterized by neural networks and are optimized by maximizing the variational lower bound using stochastic gradient descent. The effectiveness of the proposed method was demonstrated through experiments using three clustering tasks." @default.
- W3030662011 created "2020-06-05" @default.
- W3030662011 creator A5030880294 @default.
- W3030662011 creator A5034538103 @default.
- W3030662011 creator A5075849177 @default.
- W3030662011 date "2020-05-25" @default.
- W3030662011 modified "2023-09-27" @default.
- W3030662011 title "Transfer Metric Learning for Unseen Domains" @default.
- W3030662011 cites W1483597436 @default.
- W3030662011 cites W1561439832 @default.
- W3030662011 cites W1916279783 @default.
- W3030662011 cites W1920962657 @default.
- W3030662011 cites W1975517671 @default.
- W3030662011 cites W2004080111 @default.
- W3030662011 cites W2032346219 @default.
- W3030662011 cites W2056766567 @default.
- W3030662011 cites W2064675550 @default.
- W3030662011 cites W2141581971 @default.
- W3030662011 cites W2167366427 @default.
- W3030662011 cites W2169495281 @default.
- W3030662011 cites W2528430077 @default.
- W3030662011 cites W2537170730 @default.
- W3030662011 cites W2592329255 @default.
- W3030662011 cites W2763549966 @default.
- W3030662011 cites W2797344641 @default.
- W3030662011 cites W2947319827 @default.
- W3030662011 cites W2963094609 @default.
- W3030662011 cites W2963118547 @default.
- W3030662011 cites W2964105864 @default.
- W3030662011 cites W2964228922 @default.
- W3030662011 cites W4211208325 @default.
- W3030662011 doi "https://doi.org/10.1007/s41019-020-00125-1" @default.
- W3030662011 hasPublicationYear "2020" @default.
- W3030662011 type Work @default.
- W3030662011 sameAs 3030662011 @default.
- W3030662011 citedByCount "5" @default.
- W3030662011 countsByYear W30306620112021 @default.
- W3030662011 countsByYear W30306620112022 @default.
- W3030662011 countsByYear W30306620112023 @default.
- W3030662011 crossrefType "journal-article" @default.
- W3030662011 hasAuthorship W3030662011A5030880294 @default.
- W3030662011 hasAuthorship W3030662011A5034538103 @default.
- W3030662011 hasAuthorship W3030662011A5075849177 @default.
- W3030662011 hasBestOaLocation W30306620111 @default.
- W3030662011 hasConcept C11413529 @default.
- W3030662011 hasConcept C119857082 @default.
- W3030662011 hasConcept C134306372 @default.
- W3030662011 hasConcept C138885662 @default.
- W3030662011 hasConcept C150899416 @default.
- W3030662011 hasConcept C153180895 @default.
- W3030662011 hasConcept C154945302 @default.
- W3030662011 hasConcept C160920958 @default.
- W3030662011 hasConcept C162324750 @default.
- W3030662011 hasConcept C165464430 @default.
- W3030662011 hasConcept C176217482 @default.
- W3030662011 hasConcept C177264268 @default.
- W3030662011 hasConcept C199360897 @default.
- W3030662011 hasConcept C21080849 @default.
- W3030662011 hasConcept C21547014 @default.
- W3030662011 hasConcept C2776401178 @default.
- W3030662011 hasConcept C33923547 @default.
- W3030662011 hasConcept C36503486 @default.
- W3030662011 hasConcept C41008148 @default.
- W3030662011 hasConcept C41608201 @default.
- W3030662011 hasConcept C41895202 @default.
- W3030662011 hasConcept C49937458 @default.
- W3030662011 hasConcept C50644808 @default.
- W3030662011 hasConcept C83665646 @default.
- W3030662011 hasConceptScore W3030662011C11413529 @default.
- W3030662011 hasConceptScore W3030662011C119857082 @default.
- W3030662011 hasConceptScore W3030662011C134306372 @default.
- W3030662011 hasConceptScore W3030662011C138885662 @default.
- W3030662011 hasConceptScore W3030662011C150899416 @default.
- W3030662011 hasConceptScore W3030662011C153180895 @default.
- W3030662011 hasConceptScore W3030662011C154945302 @default.
- W3030662011 hasConceptScore W3030662011C160920958 @default.
- W3030662011 hasConceptScore W3030662011C162324750 @default.
- W3030662011 hasConceptScore W3030662011C165464430 @default.
- W3030662011 hasConceptScore W3030662011C176217482 @default.
- W3030662011 hasConceptScore W3030662011C177264268 @default.
- W3030662011 hasConceptScore W3030662011C199360897 @default.
- W3030662011 hasConceptScore W3030662011C21080849 @default.
- W3030662011 hasConceptScore W3030662011C21547014 @default.
- W3030662011 hasConceptScore W3030662011C2776401178 @default.
- W3030662011 hasConceptScore W3030662011C33923547 @default.
- W3030662011 hasConceptScore W3030662011C36503486 @default.
- W3030662011 hasConceptScore W3030662011C41008148 @default.
- W3030662011 hasConceptScore W3030662011C41608201 @default.
- W3030662011 hasConceptScore W3030662011C41895202 @default.
- W3030662011 hasConceptScore W3030662011C49937458 @default.
- W3030662011 hasConceptScore W3030662011C50644808 @default.
- W3030662011 hasConceptScore W3030662011C83665646 @default.
- W3030662011 hasIssue "2" @default.
- W3030662011 hasLocation W30306620111 @default.
- W3030662011 hasOpenAccess W3030662011 @default.
- W3030662011 hasPrimaryLocation W30306620111 @default.
- W3030662011 hasRelatedWork W2052253960 @default.
- W3030662011 hasRelatedWork W2147802381 @default.