Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366308455> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4366308455 abstract "Federated learning (FL) is a novel decentralized machine learning mechanism, which bridges data silos to train a global model by utilizing data and computation power of local clients in a privacy-preserving way. Moreover, to handle heterogeneous data across domains, tasks and partities, federated meta-learning (FML) has been proposed, which leverages the fast adaptation of meta-learning for transferable and customizable models. Nevertheless, most of the existing studies focus on providing personalized models for different users, leaving other important issues not well solved, especially, incentive mechanisms, which are used as a common foundation for FML to attrack and maintain high-quality and reputable clients. To fill the gap, this paper proposes a learning-based incentive mechanism for FML to motivate local clients to participate in the data federation. First, we propose to reward clients according to the amount of data they contribute to the model training. Then, to analyze the behaviors of model owner and local clients, we formulate the incentivized training task as a Stackelberg game, and design a method based on reinforcement learning (RL) to learn optimal pricing and participating strategies for the task publisher and the local clients, respectively. Lastly, extensive experiments are conducted to demonstrate the efficiency and effectiveness of the proposed RL-based incentive mechanism, which assists multiple parties to reach the equilibrium of the game designed for FML." @default.
- W4366308455 created "2023-04-20" @default.
- W4366308455 creator A5014411780 @default.
- W4366308455 creator A5017709369 @default.
- W4366308455 creator A5038431950 @default.
- W4366308455 creator A5050820825 @default.
- W4366308455 creator A5061476346 @default.
- W4366308455 date "2022-10-01" @default.
- W4366308455 modified "2023-10-16" @default.
- W4366308455 title "Reinforcement Learning Based Incentive Mechanism for Federated Meta Learning: A Game-Theoretic Perspective" @default.
- W4366308455 cites W1564711504 @default.
- W4366308455 cites W2038194220 @default.
- W4366308455 cites W2141673635 @default.
- W4366308455 cites W2602495758 @default.
- W4366308455 cites W2783525692 @default.
- W4366308455 cites W2980713544 @default.
- W4366308455 cites W2989120265 @default.
- W4366308455 cites W3001989995 @default.
- W4366308455 cites W3006453722 @default.
- W4366308455 cites W3006497973 @default.
- W4366308455 cites W3006921589 @default.
- W4366308455 cites W3008477738 @default.
- W4366308455 cites W3021573557 @default.
- W4366308455 cites W3027859434 @default.
- W4366308455 cites W3033511014 @default.
- W4366308455 cites W3095611529 @default.
- W4366308455 cites W3155681579 @default.
- W4366308455 cites W3205260830 @default.
- W4366308455 cites W4206067390 @default.
- W4366308455 cites W4224937317 @default.
- W4366308455 cites W4285170564 @default.
- W4366308455 cites W4285409316 @default.
- W4366308455 cites W4292513160 @default.
- W4366308455 doi "https://doi.org/10.1109/ictai56018.2022.00176" @default.
- W4366308455 hasPublicationYear "2022" @default.
- W4366308455 type Work @default.
- W4366308455 citedByCount "0" @default.
- W4366308455 crossrefType "proceedings-article" @default.
- W4366308455 hasAuthorship W4366308455A5014411780 @default.
- W4366308455 hasAuthorship W4366308455A5017709369 @default.
- W4366308455 hasAuthorship W4366308455A5038431950 @default.
- W4366308455 hasAuthorship W4366308455A5050820825 @default.
- W4366308455 hasAuthorship W4366308455A5061476346 @default.
- W4366308455 hasConcept C119857082 @default.
- W4366308455 hasConcept C120665830 @default.
- W4366308455 hasConcept C121332964 @default.
- W4366308455 hasConcept C127413603 @default.
- W4366308455 hasConcept C139807058 @default.
- W4366308455 hasConcept C144237770 @default.
- W4366308455 hasConcept C153517567 @default.
- W4366308455 hasConcept C154945302 @default.
- W4366308455 hasConcept C162324750 @default.
- W4366308455 hasConcept C175444787 @default.
- W4366308455 hasConcept C177142836 @default.
- W4366308455 hasConcept C199510392 @default.
- W4366308455 hasConcept C201995342 @default.
- W4366308455 hasConcept C2780451532 @default.
- W4366308455 hasConcept C2781002164 @default.
- W4366308455 hasConcept C29122968 @default.
- W4366308455 hasConcept C33923547 @default.
- W4366308455 hasConcept C41008148 @default.
- W4366308455 hasConcept C97541855 @default.
- W4366308455 hasConceptScore W4366308455C119857082 @default.
- W4366308455 hasConceptScore W4366308455C120665830 @default.
- W4366308455 hasConceptScore W4366308455C121332964 @default.
- W4366308455 hasConceptScore W4366308455C127413603 @default.
- W4366308455 hasConceptScore W4366308455C139807058 @default.
- W4366308455 hasConceptScore W4366308455C144237770 @default.
- W4366308455 hasConceptScore W4366308455C153517567 @default.
- W4366308455 hasConceptScore W4366308455C154945302 @default.
- W4366308455 hasConceptScore W4366308455C162324750 @default.
- W4366308455 hasConceptScore W4366308455C175444787 @default.
- W4366308455 hasConceptScore W4366308455C177142836 @default.
- W4366308455 hasConceptScore W4366308455C199510392 @default.
- W4366308455 hasConceptScore W4366308455C201995342 @default.
- W4366308455 hasConceptScore W4366308455C2780451532 @default.
- W4366308455 hasConceptScore W4366308455C2781002164 @default.
- W4366308455 hasConceptScore W4366308455C29122968 @default.
- W4366308455 hasConceptScore W4366308455C33923547 @default.
- W4366308455 hasConceptScore W4366308455C41008148 @default.
- W4366308455 hasConceptScore W4366308455C97541855 @default.
- W4366308455 hasFunder F4320321001 @default.
- W4366308455 hasLocation W43663084551 @default.
- W4366308455 hasOpenAccess W4366308455 @default.
- W4366308455 hasPrimaryLocation W43663084551 @default.
- W4366308455 hasRelatedWork W2102010784 @default.
- W4366308455 hasRelatedWork W3037114224 @default.
- W4366308455 hasRelatedWork W3092824172 @default.
- W4366308455 hasRelatedWork W3135704163 @default.
- W4366308455 hasRelatedWork W3200361725 @default.
- W4366308455 hasRelatedWork W4287647350 @default.
- W4366308455 hasRelatedWork W4319083788 @default.
- W4366308455 hasRelatedWork W4319309271 @default.
- W4366308455 hasRelatedWork W4323780675 @default.
- W4366308455 hasRelatedWork W49403775 @default.
- W4366308455 isParatext "false" @default.
- W4366308455 isRetracted "false" @default.
- W4366308455 workType "article" @default.