Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201798506> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3201798506 abstract "Federated Learning (FL) is a new distributed machine learning (ML) approach which enables thousands of mobile devices to collaboratively train artificial intelligence (AI) models using local data without compromising user privacy. Although FL represents a promising computing paradigm, such training process can not be fully realized without an appropriate economic mechanism that incentivizes the participation of heterogeneous clients. This work targets social cost minimization, and studies the incentive mechanism design in FL through a procurement auction. Different from existing literature, we consider a practical scenario of FL where clients are selected and scheduled at different global iterations to guarantee the completion of the FL job, and capture the distinct feature of FL that the number of global iterations is determined by the local accuracy of all participants to balance between computation and communication. Our auction framework <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$A_{FL}$</tex> first decomposes the social cost minimization problem into a series of winner determination problems (WDPs) based on the number of global iterations. Then to solve each WDP, <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$A_{FL}$</tex> invokes a greedy algorithm to determine the winners, and a payment algorithm for computing remuneration to winners. Finally, <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$A_{FL}$</tex> returns the best solution among all WDPs. Theoretical analysis proves that <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$A_{FL}$</tex> is truthful, individual rational, computationally efficient, and achieves a near-optimal social cost. We further conduct large-scale simulation studies based on the real-world data. Simulation results show that <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$A_{FL}$</tex> can reduce the social cost by up to 75% compared with state-of-the-art algorithms." @default.
- W3201798506 created "2021-10-11" @default.
- W3201798506 creator A5024396134 @default.
- W3201798506 creator A5043162940 @default.
- W3201798506 creator A5065058975 @default.
- W3201798506 creator A5066247159 @default.
- W3201798506 creator A5068489266 @default.
- W3201798506 date "2021-07-01" @default.
- W3201798506 modified "2023-10-16" @default.
- W3201798506 title "A Truthful Procurement Auction for Incentivizing Heterogeneous Clients in Federated Learning" @default.
- W3201798506 cites W1963069121 @default.
- W3201798506 cites W1970756365 @default.
- W3201798506 cites W2029050771 @default.
- W3201798506 cites W2061880373 @default.
- W3201798506 cites W2126170153 @default.
- W3201798506 cites W2199097987 @default.
- W3201798506 cites W2345814469 @default.
- W3201798506 cites W2527855297 @default.
- W3201798506 cites W2701059868 @default.
- W3201798506 cites W2769860519 @default.
- W3201798506 cites W2887790044 @default.
- W3201798506 cites W2920095265 @default.
- W3201798506 cites W2963318081 @default.
- W3201798506 cites W2972882814 @default.
- W3201798506 cites W2989120265 @default.
- W3201798506 cites W3007199357 @default.
- W3201798506 cites W3015515533 @default.
- W3201798506 cites W3036727471 @default.
- W3201798506 cites W3047304572 @default.
- W3201798506 cites W3100476433 @default.
- W3201798506 cites W3105122387 @default.
- W3201798506 cites W3112877893 @default.
- W3201798506 doi "https://doi.org/10.1109/icdcs51616.2021.00026" @default.
- W3201798506 hasPublicationYear "2021" @default.
- W3201798506 type Work @default.
- W3201798506 sameAs 3201798506 @default.
- W3201798506 citedByCount "4" @default.
- W3201798506 countsByYear W32017985062022 @default.
- W3201798506 countsByYear W32017985062023 @default.
- W3201798506 crossrefType "proceedings-article" @default.
- W3201798506 hasAuthorship W3201798506A5024396134 @default.
- W3201798506 hasAuthorship W3201798506A5043162940 @default.
- W3201798506 hasAuthorship W3201798506A5065058975 @default.
- W3201798506 hasAuthorship W3201798506A5066247159 @default.
- W3201798506 hasAuthorship W3201798506A5068489266 @default.
- W3201798506 hasConcept C10138342 @default.
- W3201798506 hasConcept C119857082 @default.
- W3201798506 hasConcept C136764020 @default.
- W3201798506 hasConcept C144237770 @default.
- W3201798506 hasConcept C145097563 @default.
- W3201798506 hasConcept C153517567 @default.
- W3201798506 hasConcept C154945302 @default.
- W3201798506 hasConcept C162324750 @default.
- W3201798506 hasConcept C163239763 @default.
- W3201798506 hasConcept C175444787 @default.
- W3201798506 hasConcept C187736073 @default.
- W3201798506 hasConcept C201650216 @default.
- W3201798506 hasConcept C2777488495 @default.
- W3201798506 hasConcept C29122968 @default.
- W3201798506 hasConcept C33923547 @default.
- W3201798506 hasConcept C41008148 @default.
- W3201798506 hasConcept C59919655 @default.
- W3201798506 hasConceptScore W3201798506C10138342 @default.
- W3201798506 hasConceptScore W3201798506C119857082 @default.
- W3201798506 hasConceptScore W3201798506C136764020 @default.
- W3201798506 hasConceptScore W3201798506C144237770 @default.
- W3201798506 hasConceptScore W3201798506C145097563 @default.
- W3201798506 hasConceptScore W3201798506C153517567 @default.
- W3201798506 hasConceptScore W3201798506C154945302 @default.
- W3201798506 hasConceptScore W3201798506C162324750 @default.
- W3201798506 hasConceptScore W3201798506C163239763 @default.
- W3201798506 hasConceptScore W3201798506C175444787 @default.
- W3201798506 hasConceptScore W3201798506C187736073 @default.
- W3201798506 hasConceptScore W3201798506C201650216 @default.
- W3201798506 hasConceptScore W3201798506C2777488495 @default.
- W3201798506 hasConceptScore W3201798506C29122968 @default.
- W3201798506 hasConceptScore W3201798506C33923547 @default.
- W3201798506 hasConceptScore W3201798506C41008148 @default.
- W3201798506 hasConceptScore W3201798506C59919655 @default.
- W3201798506 hasFunder F4320321001 @default.
- W3201798506 hasLocation W32017985061 @default.
- W3201798506 hasOpenAccess W3201798506 @default.
- W3201798506 hasPrimaryLocation W32017985061 @default.
- W3201798506 hasRelatedWork W1576552866 @default.
- W3201798506 hasRelatedWork W2056241941 @default.
- W3201798506 hasRelatedWork W2359106505 @default.
- W3201798506 hasRelatedWork W2913174645 @default.
- W3201798506 hasRelatedWork W3122761074 @default.
- W3201798506 hasRelatedWork W3123442122 @default.
- W3201798506 hasRelatedWork W3123786238 @default.
- W3201798506 hasRelatedWork W4210724065 @default.
- W3201798506 hasRelatedWork W4312590041 @default.
- W3201798506 hasRelatedWork W6674857 @default.
- W3201798506 isParatext "false" @default.
- W3201798506 isRetracted "false" @default.
- W3201798506 magId "3201798506" @default.
- W3201798506 workType "article" @default.