FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3149291386> ?p ?o ?g. }

• W3149291386 endingPage "347" @default.
• W3149291386 startingPage "323" @default.
• W3149291386 abstract "Abstract In this paper, we address the problem of privacy-preserving distributed learning and the evaluation of machine-learning models by analyzing it in the widespread MapReduce abstraction that we extend with privacy constraints. We design spindle (Scalable Privacy-preservINg Distributed LEarning), the first distributed and privacy-preserving system that covers the complete ML workflow by enabling the execution of a cooperative gradient-descent and the evaluation of the obtained model and by preserving data and model confidentiality in a passive-adversary model with up to N −1 colluding parties. spindle uses multiparty homomorphic encryption to execute parallel high-depth computations on encrypted data without significant overhead. We instantiate spindle for the training and evaluation of generalized linear models on distributed datasets and show that it is able to accurately (on par with non-secure centrally-trained models) and efficiently (due to a multi-level parallelization of the computations) train models that require a high number of iterations on large input data with thousands of features, distributed among hundreds of data providers. For instance, it trains a logistic-regression model on a dataset of one million samples with 32 features distributed among 160 data providers in less than three minutes." @default.
• W3149291386 created "2021-04-13" @default.
• W3149291386 creator A5000583679 @default.
• W3149291386 creator A5025665736 @default.
• W3149291386 creator A5031281762 @default.
• W3149291386 creator A5072336168 @default.
• W3149291386 creator A5080497445 @default.
• W3149291386 creator A5089763199 @default.
• W3149291386 creator A5091369772 @default.
• W3149291386 date "2021-01-29" @default.
• W3149291386 modified "2023-10-16" @default.
• W3149291386 title "Scalable Privacy-Preserving Distributed Learning" @default.
• W3149291386 cites W133884053 @default.
• W3149291386 cites W1617663512 @default.
• W3149291386 cites W1971991172 @default.
• W3149291386 cites W2031738616 @default.
• W3149291386 cites W2032775418 @default.
• W3149291386 cites W2051267297 @default.
• W3149291386 cites W2053637704 @default.
• W3149291386 cites W2091825929 @default.
• W3149291386 cites W2098290658 @default.
• W3149291386 cites W2106970188 @default.
• W3149291386 cites W2108834246 @default.
• W3149291386 cites W2141420453 @default.
• W3149291386 cites W2164278908 @default.
• W3149291386 cites W2167732364 @default.
• W3149291386 cites W2173213060 @default.
• W3149291386 cites W2221443338 @default.
• W3149291386 cites W2233194383 @default.
• W3149291386 cites W2295292576 @default.
• W3149291386 cites W236632755 @default.
• W3149291386 cites W2400124473 @default.
• W3149291386 cites W2400700555 @default.
• W3149291386 cites W2402235285 @default.
• W3149291386 cites W2473418344 @default.
• W3149291386 cites W2535690855 @default.
• W3149291386 cites W2587454507 @default.
• W3149291386 cites W2588978745 @default.
• W3149291386 cites W2591882872 @default.
• W3149291386 cites W2620512600 @default.
• W3149291386 cites W2701059868 @default.
• W3149291386 cites W2729599932 @default.
• W3149291386 cites W2747433492 @default.
• W3149291386 cites W2765200655 @default.
• W3149291386 cites W2766831133 @default.
• W3149291386 cites W2768174108 @default.
• W3149291386 cites W2781091734 @default.
• W3149291386 cites W2789894922 @default.
• W3149291386 cites W2793675838 @default.
• W3149291386 cites W2795097198 @default.
• W3149291386 cites W2800453812 @default.
• W3149291386 cites W2800679800 @default.
• W3149291386 cites W2801490189 @default.
• W3149291386 cites W2801491268 @default.
• W3149291386 cites W2802758511 @default.
• W3149291386 cites W2811248283 @default.
• W3149291386 cites W2883074043 @default.
• W3149291386 cites W2894784988 @default.
• W3149291386 cites W2895782209 @default.
• W3149291386 cites W2896684650 @default.
• W3149291386 cites W2896938420 @default.
• W3149291386 cites W2898108725 @default.
• W3149291386 cites W2930926105 @default.
• W3149291386 cites W2951264056 @default.
• W3149291386 cites W2954442424 @default.
• W3149291386 cites W2955023110 @default.
• W3149291386 cites W2963106566 @default.
• W3149291386 cites W2963433607 @default.
• W3149291386 cites W2963456518 @default.
• W3149291386 cites W2963752132 @default.
• W3149291386 cites W2964162474 @default.
• W3149291386 cites W2964261135 @default.
• W3149291386 cites W2970408908 @default.
• W3149291386 cites W2970606380 @default.
• W3149291386 cites W2979637109 @default.
• W3149291386 cites W2983941230 @default.
• W3149291386 cites W2985808347 @default.
• W3149291386 cites W2987932087 @default.
• W3149291386 cites W3003231116 @default.
• W3149291386 cites W3006531732 @default.
• W3149291386 cites W3010009703 @default.
• W3149291386 cites W3045310268 @default.
• W3149291386 cites W3095930832 @default.
• W3149291386 cites W3101329503 @default.
• W3149291386 cites W3125817276 @default.
• W3149291386 cites W4210719600 @default.
• W3149291386 cites W4243453402 @default.
• W3149291386 doi "https://doi.org/10.2478/popets-2021-0030" @default.
• W3149291386 hasPublicationYear "2021" @default.
• W3149291386 type Work @default.
• W3149291386 sameAs 3149291386 @default.
• W3149291386 citedByCount "16" @default.
• W3149291386 countsByYear W31492913862020 @default.
• W3149291386 countsByYear W31492913862021 @default.
• W3149291386 countsByYear W31492913862022 @default.
• W3149291386 countsByYear W31492913862023 @default.
• W3149291386 crossrefType "journal-article" @default.
• W3149291386 hasAuthorship W3149291386A5000583679 @default.

• next