FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204132485> ?p ?o ?g. }

• W3204132485 endingPage "14" @default.
• W3204132485 startingPage "1" @default.
• W3204132485 abstract "Unsupervised domain adaptation (UDA) provides a strategy for improving machine learning performance in data-rich (target) domains where ground truth labels are inaccessible but can be found in related (source) domains. In cases where meta-domain information such as label distributions is available, weak supervision can further boost performance. We propose a novel framework, CALDA, to tackle these two problems. CALDA synergistically combines the principles of contrastive learning and adversarial learning to robustly support multi-source UDA (MS-UDA) for time series data. Similar to prior methods, CALDA utilizes adversarial learning to align source and target feature representations. Unlike prior approaches, CALDA additionally leverages cross-source label information across domains. CALDA pulls examples with the same label close to each other, while pushing apart examples with different labels, reshaping the space through contrastive learning. Unlike prior contrastive adaptation methods, CALDA requires neither data augmentation nor pseudo labeling, which may be more challenging for time series. We empirically validate our proposed approach. Based on results from human activity recognition, electromyography, and synthetic datasets, we find utilizing cross-source information improves performance over prior time series and contrastive methods. Weak supervision further improves performance, even in the presence of noise, allowing CALDA to offer generalizable strategies for MS-UDA." @default.
• W3204132485 created "2021-10-11" @default.
• W3204132485 creator A5048183050 @default.
• W3204132485 creator A5055445718 @default.
• W3204132485 creator A5059791335 @default.
• W3204132485 date "2023-01-01" @default.
• W3204132485 modified "2023-09-24" @default.
• W3204132485 title "CALDA: Improving Multi-Source Time Series Domain Adaptation With Contrastive Adversarial Learning" @default.
• W3204132485 cites W134960717 @default.
• W3204132485 cites W1731081199 @default.
• W3204132485 cites W1783315696 @default.
• W3204132485 cites W2017634428 @default.
• W3204132485 cites W2057907879 @default.
• W3204132485 cites W2090805767 @default.
• W3204132485 cites W2117154949 @default.
• W3204132485 cites W2126151240 @default.
• W3204132485 cites W2138621090 @default.
• W3204132485 cites W2154368244 @default.
• W3204132485 cites W2541965240 @default.
• W3204132485 cites W2551393996 @default.
• W3204132485 cites W2589747988 @default.
• W3204132485 cites W2740222873 @default.
• W3204132485 cites W2762706434 @default.
• W3204132485 cites W2793888044 @default.
• W3204132485 cites W2842511635 @default.
• W3204132485 cites W2891691791 @default.
• W3204132485 cites W2891975605 @default.
• W3204132485 cites W2892035503 @default.
• W3204132485 cites W2897132279 @default.
• W3204132485 cites W2941567003 @default.
• W3204132485 cites W2963446520 @default.
• W3204132485 cites W2963449430 @default.
• W3204132485 cites W2963532621 @default.
• W3204132485 cites W2966743431 @default.
• W3204132485 cites W2997304337 @default.
• W3204132485 cites W3018378048 @default.
• W3204132485 cites W3034978746 @default.
• W3204132485 cites W3035524453 @default.
• W3204132485 cites W3036171739 @default.
• W3204132485 cites W3039883906 @default.
• W3204132485 cites W3045355653 @default.
• W3204132485 cites W3046296398 @default.
• W3204132485 cites W3080108946 @default.
• W3204132485 cites W3093274308 @default.
• W3204132485 cites W3100553325 @default.
• W3204132485 cites W3174632922 @default.
• W3204132485 doi "https://doi.org/10.1109/tpami.2023.3298346" @default.
• W3204132485 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37486844" @default.
• W3204132485 hasPublicationYear "2023" @default.
• W3204132485 type Work @default.
• W3204132485 sameAs 3204132485 @default.
• W3204132485 citedByCount "0" @default.
• W3204132485 crossrefType "journal-article" @default.
• W3204132485 hasAuthorship W3204132485A5048183050 @default.
• W3204132485 hasAuthorship W3204132485A5055445718 @default.
• W3204132485 hasAuthorship W3204132485A5059791335 @default.
• W3204132485 hasBestOaLocation W32041324852 @default.
• W3204132485 hasConcept C119857082 @default.
• W3204132485 hasConcept C120665830 @default.
• W3204132485 hasConcept C121332964 @default.
• W3204132485 hasConcept C134306372 @default.
• W3204132485 hasConcept C138885662 @default.
• W3204132485 hasConcept C139807058 @default.
• W3204132485 hasConcept C153180895 @default.
• W3204132485 hasConcept C154945302 @default.
• W3204132485 hasConcept C2776401178 @default.
• W3204132485 hasConcept C33923547 @default.
• W3204132485 hasConcept C36503486 @default.
• W3204132485 hasConcept C41008148 @default.
• W3204132485 hasConcept C41895202 @default.
• W3204132485 hasConceptScore W3204132485C119857082 @default.
• W3204132485 hasConceptScore W3204132485C120665830 @default.
• W3204132485 hasConceptScore W3204132485C121332964 @default.
• W3204132485 hasConceptScore W3204132485C134306372 @default.
• W3204132485 hasConceptScore W3204132485C138885662 @default.
• W3204132485 hasConceptScore W3204132485C139807058 @default.
• W3204132485 hasConceptScore W3204132485C153180895 @default.
• W3204132485 hasConceptScore W3204132485C154945302 @default.
• W3204132485 hasConceptScore W3204132485C2776401178 @default.
• W3204132485 hasConceptScore W3204132485C33923547 @default.
• W3204132485 hasConceptScore W3204132485C36503486 @default.
• W3204132485 hasConceptScore W3204132485C41008148 @default.
• W3204132485 hasConceptScore W3204132485C41895202 @default.
• W3204132485 hasLocation W32041324851 @default.
• W3204132485 hasLocation W32041324852 @default.
• W3204132485 hasLocation W32041324853 @default.
• W3204132485 hasOpenAccess W3204132485 @default.
• W3204132485 hasPrimaryLocation W32041324851 @default.
• W3204132485 hasRelatedWork W1982770690 @default.
• W3204132485 hasRelatedWork W2016461833 @default.
• W3204132485 hasRelatedWork W2052253960 @default.
• W3204132485 hasRelatedWork W2147802381 @default.
• W3204132485 hasRelatedWork W2382607599 @default.
• W3204132485 hasRelatedWork W2509918103 @default.
• W3204132485 hasRelatedWork W2546942002 @default.
• W3204132485 hasRelatedWork W2760085659 @default.
• W3204132485 hasRelatedWork W2785535669 @default.
• W3204132485 hasRelatedWork W2929240682 @default.

• next