FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208166108> ?p ?o ?g. }

• W3208166108 abstract "Federated learning (FL) has emerged as an effective solution to decentralized and privacy-preserving machine learning for mobile clients. While traditional FL has demonstrated its superiority, it ignores the non-iid (independently identically distributed) situation, which widely exists in mobile scenarios. Failing to handle non-iid situations could cause problems such as performance decreasing and possible attacks. Previous studies focus on the symptoms directly, as they try to improve the accuracy or detect possible attacks by adding extra steps to conventional FL models. However, previous techniques overlook the root causes for the symptoms: blindly aggregating models with the non-iid distributions. In this paper, we try to fundamentally address the issue by decomposing the overall non-iid situation into several iid clusters and conducting aggregation in each cluster. Specifically, we propose textbf{DistFL}, a novel framework to achieve automated and accurate textbf{Dist}ribution-aware textbf{F}ederated textbf{L}earning in a cost-efficient way. DistFL achieves clustering via extracting and comparing the textit{distribution knowledge} from the uploaded models. With this framework, we are able to generate multiple personalized models with distinctive distributions and assign them to the corresponding clients. Extensive experiments on mobile scenarios with popular model architectures have demonstrated the effectiveness of DistFL." @default.
• W3208166108 created "2021-11-08" @default.
• W3208166108 creator A5014456335 @default.
• W3208166108 creator A5014566102 @default.
• W3208166108 creator A5021450973 @default.
• W3208166108 creator A5034959009 @default.
• W3208166108 creator A5039182822 @default.
• W3208166108 creator A5053843137 @default.
• W3208166108 creator A5053944287 @default.
• W3208166108 creator A5055087680 @default.
• W3208166108 date "2021-10-22" @default.
• W3208166108 modified "2023-09-25" @default.
• W3208166108 title "DistFL: Distribution-aware Federated Learning for Mobile Scenarios" @default.
• W3208166108 cites W134960717 @default.
• W3208166108 cites W1686810756 @default.
• W3208166108 cites W1690739335 @default.
• W3208166108 cites W1821462560 @default.
• W3208166108 cites W1915485278 @default.
• W3208166108 cites W1965555277 @default.
• W3208166108 cites W2026653933 @default.
• W3208166108 cites W2108598243 @default.
• W3208166108 cites W2194775991 @default.
• W3208166108 cites W2473418344 @default.
• W3208166108 cites W2541884796 @default.
• W3208166108 cites W2591882872 @default.
• W3208166108 cites W2600383743 @default.
• W3208166108 cites W2627183927 @default.
• W3208166108 cites W2744999500 @default.
• W3208166108 cites W2753783305 @default.
• W3208166108 cites W2767079719 @default.
• W3208166108 cites W2769312802 @default.
• W3208166108 cites W2777914285 @default.
• W3208166108 cites W2807006176 @default.
• W3208166108 cites W2883059862 @default.
• W3208166108 cites W2886444620 @default.
• W3208166108 cites W2898422183 @default.
• W3208166108 cites W2900120080 @default.
• W3208166108 cites W2900319533 @default.
• W3208166108 cites W2902113386 @default.
• W3208166108 cites W2904190483 @default.
• W3208166108 cites W2911736639 @default.
• W3208166108 cites W2911752833 @default.
• W3208166108 cites W2912213068 @default.
• W3208166108 cites W2930926105 @default.
• W3208166108 cites W2942091739 @default.
• W3208166108 cites W2949506549 @default.
• W3208166108 cites W2950290344 @default.
• W3208166108 cites W2952787292 @default.
• W3208166108 cites W2962966540 @default.
• W3208166108 cites W2963456518 @default.
• W3208166108 cites W2981349114 @default.
• W3208166108 cites W2992272656 @default.
• W3208166108 cites W2995022099 @default.
• W3208166108 cites W2996800219 @default.
• W3208166108 cites W2996974038 @default.
• W3208166108 cites W2998368790 @default.
• W3208166108 cites W3006157707 @default.
• W3208166108 cites W3010262580 @default.
• W3208166108 cites W3011892127 @default.
• W3208166108 cites W3034957837 @default.
• W3208166108 cites W3037024761 @default.
• W3208166108 cites W3044211235 @default.
• W3208166108 cites W3087391814 @default.
• W3208166108 cites W3104631511 @default.
• W3208166108 cites W3108940306 @default.
• W3208166108 cites W3110209590 @default.
• W3208166108 cites W3114473259 @default.
• W3208166108 cites W3118608800 @default.
• W3208166108 cites W3134576446 @default.
• W3208166108 cites W3145363636 @default.
• W3208166108 cites W3156024711 @default.
• W3208166108 cites W3170544981 @default.
• W3208166108 cites W2981431987 @default.
• W3208166108 doi "https://doi.org/10.48550/arxiv.2110.11619" @default.
• W3208166108 hasPublicationYear "2021" @default.
• W3208166108 type Work @default.
• W3208166108 sameAs 3208166108 @default.
• W3208166108 citedByCount "0" @default.
• W3208166108 crossrefType "posted-content" @default.
• W3208166108 hasAuthorship W3208166108A5014456335 @default.
• W3208166108 hasAuthorship W3208166108A5014566102 @default.
• W3208166108 hasAuthorship W3208166108A5021450973 @default.
• W3208166108 hasAuthorship W3208166108A5034959009 @default.
• W3208166108 hasAuthorship W3208166108A5039182822 @default.
• W3208166108 hasAuthorship W3208166108A5053843137 @default.
• W3208166108 hasAuthorship W3208166108A5053944287 @default.
• W3208166108 hasAuthorship W3208166108A5055087680 @default.
• W3208166108 hasBestOaLocation W32081661081 @default.
• W3208166108 hasConcept C105795698 @default.
• W3208166108 hasConcept C110121322 @default.
• W3208166108 hasConcept C120314980 @default.
• W3208166108 hasConcept C120665830 @default.
• W3208166108 hasConcept C121332964 @default.
• W3208166108 hasConcept C122123141 @default.
• W3208166108 hasConcept C124101348 @default.
• W3208166108 hasConcept C134306372 @default.
• W3208166108 hasConcept C136764020 @default.
• W3208166108 hasConcept C141513077 @default.
• W3208166108 hasConcept C154945302 @default.
• W3208166108 hasConcept C164866538 @default.

• next