FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952228678> ?p ?o ?g. }

• W2952228678 abstract "In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks. However, a critical challenge in meta-learning is task uncertainty and heterogeneity, which can not be handled via globally sharing knowledge among tasks. In this paper, based on gradient-based meta-learning, we propose a hierarchically structured meta-learning (HSML) algorithm that explicitly tailors the transferable knowledge to different clusters of tasks. Inspired by the way human beings organize knowledge, we resort to a hierarchical task clustering structure to cluster tasks. As a result, the proposed approach not only addresses the challenge via the knowledge customization to different clusters of tasks, but also preserves knowledge generalization among a cluster of similar tasks. To tackle the changing of task relationship, in addition, we extend the hierarchical structure to a continual learning environment. The experimental results show that our approach can achieve state-of-the-art performance in both toy-regression and few-shot image classification problems." @default.
• W2952228678 created "2019-06-27" @default.
• W2952228678 creator A5011883201 @default.
• W2952228678 creator A5016516907 @default.
• W2952228678 creator A5051534896 @default.
• W2952228678 creator A5068865316 @default.
• W2952228678 date "2019-05-13" @default.
• W2952228678 modified "2023-09-27" @default.
• W2952228678 title "Hierarchically Structured Meta-learning" @default.
• W2952228678 cites W1514535095 @default.
• W2952228678 cites W1621791442 @default.
• W2952228678 cites W1797268635 @default.
• W2952228678 cites W1799366690 @default.
• W2952228678 cites W1846799578 @default.
• W2952228678 cites W1942758450 @default.
• W2952228678 cites W2008094377 @default.
• W2952228678 cites W2047643928 @default.
• W2952228678 cites W2086710210 @default.
• W2952228678 cites W2170789952 @default.
• W2952228678 cites W2187089797 @default.
• W2952228678 cites W2402144811 @default.
• W2952228678 cites W2409744450 @default.
• W2952228678 cites W2472819217 @default.
• W2952228678 cites W2509517678 @default.
• W2952228678 cites W2601450892 @default.
• W2952228678 cites W2624431344 @default.
• W2952228678 cites W2742093937 @default.
• W2952228678 cites W2753160622 @default.
• W2952228678 cites W2766363782 @default.
• W2952228678 cites W2770468159 @default.
• W2952228678 cites W2784596339 @default.
• W2952228678 cites W2787501667 @default.
• W2952228678 cites W2794363191 @default.
• W2952228678 cites W2804822090 @default.
• W2952228678 cites W2811124557 @default.
• W2952228678 cites W2904167876 @default.
• W2952228678 cites W2950291451 @default.
• W2952228678 cites W2950602341 @default.
• W2952228678 cites W2952518244 @default.
• W2952228678 cites W2962767366 @default.
• W2952228678 cites W2962923325 @default.
• W2952228678 cites W2963088995 @default.
• W2952228678 cites W2963341924 @default.
• W2952228678 cites W2963540014 @default.
• W2952228678 cites W2963551321 @default.
• W2952228678 cites W2963580001 @default.
• W2952228678 cites W2963775850 @default.
• W2952228678 cites W2963918774 @default.
• W2952228678 cites W2963921132 @default.
• W2952228678 cites W2964105864 @default.
• W2952228678 cites W2964121937 @default.
• W2952228678 cites W2964188247 @default.
• W2952228678 cites W3037856073 @default.
• W2952228678 hasPublicationYear "2019" @default.
• W2952228678 type Work @default.
• W2952228678 sameAs 2952228678 @default.
• W2952228678 citedByCount "8" @default.
• W2952228678 countsByYear W29522286782019 @default.
• W2952228678 countsByYear W29522286782020 @default.
• W2952228678 countsByYear W29522286782021 @default.
• W2952228678 crossrefType "posted-content" @default.
• W2952228678 hasAuthorship W2952228678A5011883201 @default.
• W2952228678 hasAuthorship W2952228678A5016516907 @default.
• W2952228678 hasAuthorship W2952228678A5051534896 @default.
• W2952228678 hasAuthorship W2952228678A5068865316 @default.
• W2952228678 hasConcept C119857082 @default.
• W2952228678 hasConcept C127413603 @default.
• W2952228678 hasConcept C134306372 @default.
• W2952228678 hasConcept C136764020 @default.
• W2952228678 hasConcept C154945302 @default.
• W2952228678 hasConcept C177148314 @default.
• W2952228678 hasConcept C183003079 @default.
• W2952228678 hasConcept C201995342 @default.
• W2952228678 hasConcept C2780451532 @default.
• W2952228678 hasConcept C2781002164 @default.
• W2952228678 hasConcept C33923547 @default.
• W2952228678 hasConcept C41008148 @default.
• W2952228678 hasConcept C73555534 @default.
• W2952228678 hasConcept C92835128 @default.
• W2952228678 hasConceptScore W2952228678C119857082 @default.
• W2952228678 hasConceptScore W2952228678C127413603 @default.
• W2952228678 hasConceptScore W2952228678C134306372 @default.
• W2952228678 hasConceptScore W2952228678C136764020 @default.
• W2952228678 hasConceptScore W2952228678C154945302 @default.
• W2952228678 hasConceptScore W2952228678C177148314 @default.
• W2952228678 hasConceptScore W2952228678C183003079 @default.
• W2952228678 hasConceptScore W2952228678C201995342 @default.
• W2952228678 hasConceptScore W2952228678C2780451532 @default.
• W2952228678 hasConceptScore W2952228678C2781002164 @default.
• W2952228678 hasConceptScore W2952228678C33923547 @default.
• W2952228678 hasConceptScore W2952228678C41008148 @default.
• W2952228678 hasConceptScore W2952228678C73555534 @default.
• W2952228678 hasConceptScore W2952228678C92835128 @default.
• W2952228678 hasLocation W29522286781 @default.
• W2952228678 hasOpenAccess W2952228678 @default.
• W2952228678 hasPrimaryLocation W29522286781 @default.
• W2952228678 hasRelatedWork W2604763608 @default.
• W2952228678 hasRelatedWork W2753160622 @default.
• W2952228678 hasRelatedWork W2787501667 @default.
• W2952228678 hasRelatedWork W2790355818 @default.

• next