FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313593185> ?p ?o ?g. }

• W4313593185 endingPage "109271" @default.
• W4313593185 startingPage "109271" @default.
• W4313593185 abstract "Multi-Source Domain Adaptation (MSDA) aims at training a classification model that achieves small target error, by leveraging labeled data from multiple source domains and unlabeled data from a target domain. The source and target domains are described by related but different joint distributions, which lie on a Riemannian manifold named the statistical manifold. In this paper, we characterize the joint distribution difference by the Hellinger distance, which bears strong connection to the Riemannian metric defined on the statistical manifold. We show that the target error of a neural network classification model is upper bounded by the average source error of the model and the average Hellinger distance, i.e., the average of multiple Hellinger distances between the source and target joint distributions in the network representation space. Motivated by the error bound, we introduce Riemannian Representation Learning (RRL): An approach that trains the network model by minimizing (i) the average empirical Hellinger distance with respect to the representation function, and (ii) the average empirical source error with respect to the network model. Specifically, we derive the average empirical Hellinger distance by constructing and solving unconstrained convex optimization problems whose global optimal solutions are easy to find. With the network model trained, we expect it to achieve small error in the target domain. Our experimental results on several image datasets demonstrate that the proposed RRL approach is statistically better than the comparison methods." @default.
• W4313593185 created "2023-01-06" @default.
• W4313593185 creator A5055442726 @default.
• W4313593185 creator A5056588022 @default.
• W4313593185 creator A5089907983 @default.
• W4313593185 date "2023-05-01" @default.
• W4313593185 modified "2023-10-09" @default.
• W4313593185 title "Riemannian representation learning for multi-source domain adaptation" @default.
• W4313593185 cites W2104094955 @default.
• W4313593185 cites W2979509742 @default.
• W4313593185 cites W3001280569 @default.
• W4313593185 cites W3021632667 @default.
• W4313593185 cites W3047993974 @default.
• W4313593185 cites W3137966214 @default.
• W4313593185 cites W3216093271 @default.
• W4313593185 cites W4213440574 @default.
• W4313593185 cites W4225743918 @default.
• W4313593185 cites W4293378572 @default.
• W4313593185 cites W4298111403 @default.
• W4313593185 cites W4324114339 @default.
• W4313593185 doi "https://doi.org/10.1016/j.patcog.2022.109271" @default.
• W4313593185 hasPublicationYear "2023" @default.
• W4313593185 type Work @default.
• W4313593185 citedByCount "2" @default.
• W4313593185 countsByYear W43135931852023 @default.
• W4313593185 crossrefType "journal-article" @default.
• W4313593185 hasAuthorship W4313593185A5055442726 @default.
• W4313593185 hasAuthorship W4313593185A5056588022 @default.
• W4313593185 hasAuthorship W4313593185A5089907983 @default.
• W4313593185 hasConcept C105795698 @default.
• W4313593185 hasConcept C109546454 @default.
• W4313593185 hasConcept C11413529 @default.
• W4313593185 hasConcept C12520029 @default.
• W4313593185 hasConcept C127413603 @default.
• W4313593185 hasConcept C134306372 @default.
• W4313593185 hasConcept C153024298 @default.
• W4313593185 hasConcept C153180895 @default.
• W4313593185 hasConcept C154945302 @default.
• W4313593185 hasConcept C162324750 @default.
• W4313593185 hasConcept C169391604 @default.
• W4313593185 hasConcept C176217482 @default.
• W4313593185 hasConcept C17744445 @default.
• W4313593185 hasConcept C18653775 @default.
• W4313593185 hasConcept C195065555 @default.
• W4313593185 hasConcept C199539241 @default.
• W4313593185 hasConcept C21547014 @default.
• W4313593185 hasConcept C2524010 @default.
• W4313593185 hasConcept C2776359362 @default.
• W4313593185 hasConcept C2779593128 @default.
• W4313593185 hasConcept C28826006 @default.
• W4313593185 hasConcept C33923547 @default.
• W4313593185 hasConcept C34388435 @default.
• W4313593185 hasConcept C36503486 @default.
• W4313593185 hasConcept C41008148 @default.
• W4313593185 hasConcept C50644808 @default.
• W4313593185 hasConcept C529865628 @default.
• W4313593185 hasConcept C78519656 @default.
• W4313593185 hasConcept C94625758 @default.
• W4313593185 hasConceptScore W4313593185C105795698 @default.
• W4313593185 hasConceptScore W4313593185C109546454 @default.
• W4313593185 hasConceptScore W4313593185C11413529 @default.
• W4313593185 hasConceptScore W4313593185C12520029 @default.
• W4313593185 hasConceptScore W4313593185C127413603 @default.
• W4313593185 hasConceptScore W4313593185C134306372 @default.
• W4313593185 hasConceptScore W4313593185C153024298 @default.
• W4313593185 hasConceptScore W4313593185C153180895 @default.
• W4313593185 hasConceptScore W4313593185C154945302 @default.
• W4313593185 hasConceptScore W4313593185C162324750 @default.
• W4313593185 hasConceptScore W4313593185C169391604 @default.
• W4313593185 hasConceptScore W4313593185C176217482 @default.
• W4313593185 hasConceptScore W4313593185C17744445 @default.
• W4313593185 hasConceptScore W4313593185C18653775 @default.
• W4313593185 hasConceptScore W4313593185C195065555 @default.
• W4313593185 hasConceptScore W4313593185C199539241 @default.
• W4313593185 hasConceptScore W4313593185C21547014 @default.
• W4313593185 hasConceptScore W4313593185C2524010 @default.
• W4313593185 hasConceptScore W4313593185C2776359362 @default.
• W4313593185 hasConceptScore W4313593185C2779593128 @default.
• W4313593185 hasConceptScore W4313593185C28826006 @default.
• W4313593185 hasConceptScore W4313593185C33923547 @default.
• W4313593185 hasConceptScore W4313593185C34388435 @default.
• W4313593185 hasConceptScore W4313593185C36503486 @default.
• W4313593185 hasConceptScore W4313593185C41008148 @default.
• W4313593185 hasConceptScore W4313593185C50644808 @default.
• W4313593185 hasConceptScore W4313593185C529865628 @default.
• W4313593185 hasConceptScore W4313593185C78519656 @default.
• W4313593185 hasConceptScore W4313593185C94625758 @default.
• W4313593185 hasFunder F4320310972 @default.
• W4313593185 hasFunder F4320321001 @default.
• W4313593185 hasLocation W43135931851 @default.
• W4313593185 hasOpenAccess W4313593185 @default.
• W4313593185 hasPrimaryLocation W43135931851 @default.
• W4313593185 hasRelatedWork W1975282624 @default.
• W4313593185 hasRelatedWork W2136739711 @default.
• W4313593185 hasRelatedWork W2155379735 @default.
• W4313593185 hasRelatedWork W2546668543 @default.
• W4313593185 hasRelatedWork W2808583987 @default.
• W4313593185 hasRelatedWork W2950223765 @default.

• next