FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4280494975> ?p ?o ?g. }

• W4280494975 endingPage "102555" @default.
• W4280494975 startingPage "102555" @default.
• W4280494975 abstract "In this paper, we propose a new algorithm for learning over distributed data such as in the IoT environment, in a privacy-preserving way. Our algorithm is a differentially private variant of distributed synchronous stochastic gradient descent method with multiple workers and one parameter server, and has the following two features: (1) each distributed worker only needs to send as small as O(1) gradients in each iteration, so that the communication from worker to server is modest; (2) the dataset of each worker is protected quantitatively by differential privacy. We mathematically prove the convergence of our algorithm, and experimentally verify that it converges and reaches standard testing results on a benchmark dataset, while simultaneously maintaining reasonable privacy budgets. Our results address two equally important issues in the IoT environment, communication efficiency and differential privacy, and potentially help reducing the tension caused by the issues." @default.
• W4280494975 created "2022-05-22" @default.
• W4280494975 creator A5068171354 @default.
• W4280494975 creator A5077849046 @default.
• W4280494975 date "2022-07-01" @default.
• W4280494975 modified "2023-09-29" @default.
• W4280494975 title "Distributed differentially-private learning with communication efficiency" @default.
• W4280494975 cites W1497601926 @default.
• W4280494975 cites W1515782956 @default.
• W4280494975 cites W1982063824 @default.
• W4280494975 cites W2053637704 @default.
• W4280494975 cites W2481704219 @default.
• W4280494975 cites W2535690855 @default.
• W4280494975 cites W2567951755 @default.
• W4280494975 cites W2767079719 @default.
• W4280494975 cites W2781091734 @default.
• W4280494975 cites W2790448487 @default.
• W4280494975 cites W2884943453 @default.
• W4280494975 cites W2913608349 @default.
• W4280494975 cites W2989289980 @default.
• W4280494975 cites W3012534984 @default.
• W4280494975 cites W3015113389 @default.
• W4280494975 cites W3016632787 @default.
• W4280494975 cites W3027472889 @default.
• W4280494975 cites W3034106913 @default.
• W4280494975 cites W3045674654 @default.
• W4280494975 cites W3111192549 @default.
• W4280494975 cites W3128083813 @default.
• W4280494975 cites W3162819349 @default.
• W4280494975 cites W3171020093 @default.
• W4280494975 cites W3172612645 @default.
• W4280494975 cites W3200840849 @default.
• W4280494975 cites W4206912802 @default.
• W4280494975 doi "https://doi.org/10.1016/j.sysarc.2022.102555" @default.
• W4280494975 hasPublicationYear "2022" @default.
• W4280494975 type Work @default.
• W4280494975 citedByCount "5" @default.
• W4280494975 countsByYear W42804949752022 @default.
• W4280494975 countsByYear W42804949752023 @default.
• W4280494975 crossrefType "journal-article" @default.
• W4280494975 hasAuthorship W4280494975A5068171354 @default.
• W4280494975 hasAuthorship W4280494975A5077849046 @default.
• W4280494975 hasConcept C11413529 @default.
• W4280494975 hasConcept C120314980 @default.
• W4280494975 hasConcept C127413603 @default.
• W4280494975 hasConcept C130120984 @default.
• W4280494975 hasConcept C13280743 @default.
• W4280494975 hasConcept C146978453 @default.
• W4280494975 hasConcept C154945302 @default.
• W4280494975 hasConcept C15744967 @default.
• W4280494975 hasConcept C162324750 @default.
• W4280494975 hasConcept C185798385 @default.
• W4280494975 hasConcept C19417346 @default.
• W4280494975 hasConcept C205649164 @default.
• W4280494975 hasConcept C206688291 @default.
• W4280494975 hasConcept C23130292 @default.
• W4280494975 hasConcept C2777303404 @default.
• W4280494975 hasConcept C2779582901 @default.
• W4280494975 hasConcept C2992525071 @default.
• W4280494975 hasConcept C3739613 @default.
• W4280494975 hasConcept C41008148 @default.
• W4280494975 hasConcept C50522688 @default.
• W4280494975 hasConcept C50644808 @default.
• W4280494975 hasConcept C93226319 @default.
• W4280494975 hasConceptScore W4280494975C11413529 @default.
• W4280494975 hasConceptScore W4280494975C120314980 @default.
• W4280494975 hasConceptScore W4280494975C127413603 @default.
• W4280494975 hasConceptScore W4280494975C130120984 @default.
• W4280494975 hasConceptScore W4280494975C13280743 @default.
• W4280494975 hasConceptScore W4280494975C146978453 @default.
• W4280494975 hasConceptScore W4280494975C154945302 @default.
• W4280494975 hasConceptScore W4280494975C15744967 @default.
• W4280494975 hasConceptScore W4280494975C162324750 @default.
• W4280494975 hasConceptScore W4280494975C185798385 @default.
• W4280494975 hasConceptScore W4280494975C19417346 @default.
• W4280494975 hasConceptScore W4280494975C205649164 @default.
• W4280494975 hasConceptScore W4280494975C206688291 @default.
• W4280494975 hasConceptScore W4280494975C23130292 @default.
• W4280494975 hasConceptScore W4280494975C2777303404 @default.
• W4280494975 hasConceptScore W4280494975C2779582901 @default.
• W4280494975 hasConceptScore W4280494975C2992525071 @default.
• W4280494975 hasConceptScore W4280494975C3739613 @default.
• W4280494975 hasConceptScore W4280494975C41008148 @default.
• W4280494975 hasConceptScore W4280494975C50522688 @default.
• W4280494975 hasConceptScore W4280494975C50644808 @default.
• W4280494975 hasConceptScore W4280494975C93226319 @default.
• W4280494975 hasFunder F4320334789 @default.
• W4280494975 hasFunder F4320338075 @default.
• W4280494975 hasLocation W42804949751 @default.
• W4280494975 hasOpenAccess W4280494975 @default.
• W4280494975 hasPrimaryLocation W42804949751 @default.
• W4280494975 hasRelatedWork W1485627940 @default.
• W4280494975 hasRelatedWork W2151520847 @default.
• W4280494975 hasRelatedWork W2385146268 @default.
• W4280494975 hasRelatedWork W2889666525 @default.
• W4280494975 hasRelatedWork W2903089346 @default.
• W4280494975 hasRelatedWork W3210483234 @default.
• W4280494975 hasRelatedWork W4220842548 @default.

• next