FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3128982022> ?p ?o ?g. }

• W3128982022 endingPage "109396" @default.
• W3128982022 startingPage "109396" @default.
• W3128982022 abstract "Heterogeneous multi-task learning (HMTL) is an important topic in multi-task learning (MTL). Most existing HMTL methods usually solve either scenario where all tasks reside in the same input (feature) space yet unnecessarily the consistent output (label) space or scenario where their input (feature) spaces are heterogeneous while the output (label) space is consistent. However, to the best of our knowledge, there is limited study on twofold heterogeneous MTL (THMTL) scenario where the input and the output spaces are both inconsistent or heterogeneous. In order to handle this complicated scenario, in this paper, we design a simple and effective multi-task adaptive learning (MTAL) network to learn multiple tasks in such THMTL setting. Specifically, we explore and utilize the inherent relationship between tasks for knowledge sharing from similar convolution kernels in individual layers of the MTAL network. To realize the sharing, we weightedly aggregate any pair of convolutional kernels with their similarity greater than some threshold ρ. Consequently, our model effectively performs cross-task learning while suppresses the intra-redundancy of the entire network. Finally, we conduct end-to-end training. Our experimental results demonstrate the significant competitiveness of our method in comparison with the current state-of-the-art methods." @default.
• W3128982022 created "2021-02-15" @default.
• W3128982022 creator A5029012645 @default.
• W3128982022 creator A5031725549 @default.
• W3128982022 date "2022-09-01" @default.
• W3128982022 modified "2023-10-16" @default.
• W3128982022 title "Learning twofold heterogeneous multi-task by sharing similar convolution kernel pairs" @default.
• W3128982022 cites W118019982 @default.
• W3128982022 cites W1905829557 @default.
• W3128982022 cites W2085348055 @default.
• W3128982022 cites W2104657103 @default.
• W3128982022 cites W2143419558 @default.
• W3128982022 cites W2251324968 @default.
• W3128982022 cites W2763933010 @default.
• W3128982022 cites W2808168148 @default.
• W3128982022 cites W2809290718 @default.
• W3128982022 cites W2962786991 @default.
• W3128982022 cites W2963430933 @default.
• W3128982022 cites W2963877604 @default.
• W3128982022 cites W2964189431 @default.
• W3128982022 cites W2964247799 @default.
• W3128982022 cites W2998103904 @default.
• W3128982022 cites W3047855687 @default.
• W3128982022 cites W3092571060 @default.
• W3128982022 cites W3101584909 @default.
• W3128982022 cites W3131397654 @default.
• W3128982022 cites W3155127799 @default.
• W3128982022 cites W3160757516 @default.
• W3128982022 cites W3175015879 @default.
• W3128982022 cites W3175432034 @default.
• W3128982022 cites W3198966012 @default.
• W3128982022 cites W3202623779 @default.
• W3128982022 cites W3209925794 @default.
• W3128982022 doi "https://doi.org/10.1016/j.knosys.2022.109396" @default.
• W3128982022 hasPublicationYear "2022" @default.
• W3128982022 type Work @default.
• W3128982022 sameAs 3128982022 @default.
• W3128982022 citedByCount "1" @default.
• W3128982022 countsByYear W31289820222023 @default.
• W3128982022 crossrefType "journal-article" @default.
• W3128982022 hasAuthorship W3128982022A5029012645 @default.
• W3128982022 hasAuthorship W3128982022A5031725549 @default.
• W3128982022 hasBestOaLocation W31289820222 @default.
• W3128982022 hasConcept C111919701 @default.
• W3128982022 hasConcept C114614502 @default.
• W3128982022 hasConcept C119857082 @default.
• W3128982022 hasConcept C138885662 @default.
• W3128982022 hasConcept C152124472 @default.
• W3128982022 hasConcept C154945302 @default.
• W3128982022 hasConcept C159985019 @default.
• W3128982022 hasConcept C162324750 @default.
• W3128982022 hasConcept C187736073 @default.
• W3128982022 hasConcept C192562407 @default.
• W3128982022 hasConcept C2776401178 @default.
• W3128982022 hasConcept C2780451532 @default.
• W3128982022 hasConcept C28006648 @default.
• W3128982022 hasConcept C33923547 @default.
• W3128982022 hasConcept C41008148 @default.
• W3128982022 hasConcept C41895202 @default.
• W3128982022 hasConcept C45347329 @default.
• W3128982022 hasConcept C4679612 @default.
• W3128982022 hasConcept C50644808 @default.
• W3128982022 hasConcept C74193536 @default.
• W3128982022 hasConceptScore W3128982022C111919701 @default.
• W3128982022 hasConceptScore W3128982022C114614502 @default.
• W3128982022 hasConceptScore W3128982022C119857082 @default.
• W3128982022 hasConceptScore W3128982022C138885662 @default.
• W3128982022 hasConceptScore W3128982022C152124472 @default.
• W3128982022 hasConceptScore W3128982022C154945302 @default.
• W3128982022 hasConceptScore W3128982022C159985019 @default.
• W3128982022 hasConceptScore W3128982022C162324750 @default.
• W3128982022 hasConceptScore W3128982022C187736073 @default.
• W3128982022 hasConceptScore W3128982022C192562407 @default.
• W3128982022 hasConceptScore W3128982022C2776401178 @default.
• W3128982022 hasConceptScore W3128982022C2780451532 @default.
• W3128982022 hasConceptScore W3128982022C28006648 @default.
• W3128982022 hasConceptScore W3128982022C33923547 @default.
• W3128982022 hasConceptScore W3128982022C41008148 @default.
• W3128982022 hasConceptScore W3128982022C41895202 @default.
• W3128982022 hasConceptScore W3128982022C45347329 @default.
• W3128982022 hasConceptScore W3128982022C4679612 @default.
• W3128982022 hasConceptScore W3128982022C50644808 @default.
• W3128982022 hasConceptScore W3128982022C74193536 @default.
• W3128982022 hasFunder F4320321001 @default.
• W3128982022 hasFunder F4320322769 @default.
• W3128982022 hasFunder F4320335440 @default.
• W3128982022 hasLocation W31289820221 @default.
• W3128982022 hasLocation W31289820222 @default.
• W3128982022 hasOpenAccess W3128982022 @default.
• W3128982022 hasPrimaryLocation W31289820221 @default.
• W3128982022 hasRelatedWork W2774059718 @default.
• W3128982022 hasRelatedWork W2798110502 @default.
• W3128982022 hasRelatedWork W2961085424 @default.
• W3128982022 hasRelatedWork W3005676475 @default.
• W3128982022 hasRelatedWork W3193517282 @default.
• W3128982022 hasRelatedWork W3200361725 @default.
• W3128982022 hasRelatedWork W4213073923 @default.
• W3128982022 hasRelatedWork W4293056039 @default.

• next