Matches in SemOpenAlex for { <https://semopenalex.org/work/W2898895571> ?p ?o ?g. }
- W2898895571 endingPage "20" @default.
- W2898895571 startingPage "1" @default.
- W2898895571 abstract "Learning from very few samples is a challenge for machine learning tasks, such as text and image classification. Performance of such task can be enhanced via transfer of helpful knowledge from related domains, which is referred to as transfer learning. In previous transfer learning works, instance transfer learning algorithms mostly focus on selecting the source domain instances similar to the target domain instances for transfer. However, the selected instances usually do not directly contribute to the learning performance in the target domain. Hypothesis transfer learning algorithms focus on the model/parameter level transfer. They treat the source hypotheses as well-trained and transfer their knowledge in terms of parameters to learn the target hypothesis. Such algorithms directly optimize the target hypothesis by the observable performance improvements. However, they fail to consider the problem that instances that contribute to the source hypotheses may be harmful for the target hypothesis, as instance transfer learning analyzed. To relieve the aforementioned problems, we propose a novel transfer learning algorithm, which follows an analogical strategy. Particularly, the proposed algorithm first learns a revised source hypothesis with only instances contributing to the target hypothesis. Then, the proposed algorithm transfers both the revised source hypothesis and the target hypothesis (only trained with a few samples) to learn an analogical hypothesis. We denote our algorithm as Analogical Transfer Learning. Extensive experiments on one synthetic dataset and three real-world benchmark datasets demonstrate the superior performance of the proposed algorithm." @default.
- W2898895571 created "2018-11-09" @default.
- W2898895571 creator A5005421447 @default.
- W2898895571 creator A5034967388 @default.
- W2898895571 creator A5045007670 @default.
- W2898895571 creator A5048411184 @default.
- W2898895571 creator A5062546146 @default.
- W2898895571 date "2018-10-29" @default.
- W2898895571 modified "2023-10-18" @default.
- W2898895571 title "Few-Shot Text and Image Classification via Analogical Transfer Learning" @default.
- W2898895571 cites W108615132 @default.
- W2898895571 cites W1919803322 @default.
- W2898895571 cites W1966026565 @default.
- W2898895571 cites W1978993121 @default.
- W2898895571 cites W1988348003 @default.
- W2898895571 cites W2008056655 @default.
- W2898895571 cites W2013044826 @default.
- W2898895571 cites W2016313676 @default.
- W2898895571 cites W2021326137 @default.
- W2898895571 cites W2045724293 @default.
- W2898895571 cites W2050549724 @default.
- W2898895571 cites W2062179223 @default.
- W2898895571 cites W2087977130 @default.
- W2898895571 cites W2122156965 @default.
- W2898895571 cites W2122838776 @default.
- W2898895571 cites W2147034979 @default.
- W2898895571 cites W2153635508 @default.
- W2898895571 cites W2159570078 @default.
- W2898895571 cites W2159630904 @default.
- W2898895571 cites W2162651021 @default.
- W2898895571 cites W2165698076 @default.
- W2898895571 cites W2166344886 @default.
- W2898895571 cites W2214871046 @default.
- W2898895571 cites W2246035736 @default.
- W2898895571 cites W2253188500 @default.
- W2898895571 cites W2292976057 @default.
- W2898895571 cites W2331050942 @default.
- W2898895571 cites W2508497007 @default.
- W2898895571 cites W2509517678 @default.
- W2898895571 cites W2509591188 @default.
- W2898895571 cites W2520436654 @default.
- W2898895571 cites W2520861906 @default.
- W2898895571 cites W2552765257 @default.
- W2898895571 cites W2566349545 @default.
- W2898895571 cites W2582553469 @default.
- W2898895571 cites W2588646734 @default.
- W2898895571 cites W2592222102 @default.
- W2898895571 cites W2596142952 @default.
- W2898895571 cites W2619145493 @default.
- W2898895571 cites W2739250163 @default.
- W2898895571 cites W2766187676 @default.
- W2898895571 cites W2795832645 @default.
- W2898895571 cites W2804847616 @default.
- W2898895571 doi "https://doi.org/10.1145/3230709" @default.
- W2898895571 hasPublicationYear "2018" @default.
- W2898895571 type Work @default.
- W2898895571 sameAs 2898895571 @default.
- W2898895571 citedByCount "9" @default.
- W2898895571 countsByYear W28988955712020 @default.
- W2898895571 countsByYear W28988955712021 @default.
- W2898895571 countsByYear W28988955712022 @default.
- W2898895571 countsByYear W28988955712023 @default.
- W2898895571 crossrefType "journal-article" @default.
- W2898895571 hasAuthorship W2898895571A5005421447 @default.
- W2898895571 hasAuthorship W2898895571A5034967388 @default.
- W2898895571 hasAuthorship W2898895571A5045007670 @default.
- W2898895571 hasAuthorship W2898895571A5048411184 @default.
- W2898895571 hasAuthorship W2898895571A5062546146 @default.
- W2898895571 hasConcept C119857082 @default.
- W2898895571 hasConcept C120665830 @default.
- W2898895571 hasConcept C121332964 @default.
- W2898895571 hasConcept C13280743 @default.
- W2898895571 hasConcept C134306372 @default.
- W2898895571 hasConcept C138885662 @default.
- W2898895571 hasConcept C144133560 @default.
- W2898895571 hasConcept C150899416 @default.
- W2898895571 hasConcept C154945302 @default.
- W2898895571 hasConcept C155202549 @default.
- W2898895571 hasConcept C162324750 @default.
- W2898895571 hasConcept C171041071 @default.
- W2898895571 hasConcept C173608175 @default.
- W2898895571 hasConcept C185798385 @default.
- W2898895571 hasConcept C187736073 @default.
- W2898895571 hasConcept C188888258 @default.
- W2898895571 hasConcept C192209626 @default.
- W2898895571 hasConcept C19966478 @default.
- W2898895571 hasConcept C205649164 @default.
- W2898895571 hasConcept C2776175482 @default.
- W2898895571 hasConcept C2779066501 @default.
- W2898895571 hasConcept C2779178101 @default.
- W2898895571 hasConcept C2780451532 @default.
- W2898895571 hasConcept C33923547 @default.
- W2898895571 hasConcept C36503486 @default.
- W2898895571 hasConcept C41008148 @default.
- W2898895571 hasConcept C41895202 @default.
- W2898895571 hasConcept C77075516 @default.
- W2898895571 hasConcept C90509273 @default.
- W2898895571 hasConceptScore W2898895571C119857082 @default.