Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100553354> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3100553354 abstract "Users of a personalised recommendation system face a dilemma: recommendations can be improved by learning from data, but only if other users are willing to share their private information. Good personalised predictions are vitally important in precision medicine, but genomic information on which the predictions are based is also particularly sensitive, as it directly identifies the patients and hence cannot easily be anonymised. Differential privacy has emerged as a potentially promising solution: privacy is considered sufficient if presence of individual patients cannot be distinguished. However, differentially private learning with current methods does not improve predictions with feasible data sizes and dimensionalities. We show that useful predictors can be learned under powerful differential privacy guarantees, and even from moderately-sized data sets, by demonstrating significant improvements in the accuracy of private drug sensitivity prediction with a new robust private regression method. Our method matches the predictive accuracy of the state-of-the-art non-private lasso regression using only 4x more samples under relatively strong differential privacy guarantees. Good performance with limited data is achieved by limiting the sharing of private information by decreasing the dimensionality and by projecting outliers to fit tighter bounds, therefore needing to add less noise for equal privacy. The proposed differentially private regression method combines theoretical appeal and asymptotic efficiency with good prediction accuracy even with moderate-sized data. As already the simple-to-implement method shows promise on the challenging genomic data, we anticipate rapid progress towards practical applications in many fields. This article was reviewed by Zoltan Gaspari and David Kreil." @default.
- W3100553354 created "2020-11-23" @default.
- W3100553354 creator A5003134529 @default.
- W3100553354 creator A5010473905 @default.
- W3100553354 creator A5018305257 @default.
- W3100553354 creator A5028197135 @default.
- W3100553354 creator A5071329195 @default.
- W3100553354 date "2018-02-06" @default.
- W3100553354 modified "2023-10-16" @default.
- W3100553354 title "Efficient differentially private learning improves drug sensitivity prediction" @default.
- W3100553354 cites W1473189865 @default.
- W3100553354 cites W1873763122 @default.
- W3100553354 cites W1987521207 @default.
- W3100553354 cites W2010523825 @default.
- W3100553354 cites W2024622963 @default.
- W3100553354 cites W2031533839 @default.
- W3100553354 cites W2040228409 @default.
- W3100553354 cites W2108068107 @default.
- W3100553354 cites W2108933868 @default.
- W3100553354 cites W2124940696 @default.
- W3100553354 cites W2125789330 @default.
- W3100553354 cites W2127555295 @default.
- W3100553354 cites W2134167315 @default.
- W3100553354 cites W2136114025 @default.
- W3100553354 cites W2139776930 @default.
- W3100553354 cites W2151320232 @default.
- W3100553354 cites W2161229593 @default.
- W3100553354 cites W2168610667 @default.
- W3100553354 cites W2217402295 @default.
- W3100553354 cites W2254169419 @default.
- W3100553354 cites W2304501949 @default.
- W3100553354 cites W4205228770 @default.
- W3100553354 doi "https://doi.org/10.1186/s13062-017-0203-4" @default.
- W3100553354 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/5801888" @default.
- W3100553354 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29409513" @default.
- W3100553354 hasPublicationYear "2018" @default.
- W3100553354 type Work @default.
- W3100553354 sameAs 3100553354 @default.
- W3100553354 citedByCount "13" @default.
- W3100553354 countsByYear W31005533542019 @default.
- W3100553354 countsByYear W31005533542020 @default.
- W3100553354 countsByYear W31005533542021 @default.
- W3100553354 countsByYear W31005533542022 @default.
- W3100553354 countsByYear W31005533542023 @default.
- W3100553354 crossrefType "journal-article" @default.
- W3100553354 hasAuthorship W3100553354A5003134529 @default.
- W3100553354 hasAuthorship W3100553354A5010473905 @default.
- W3100553354 hasAuthorship W3100553354A5018305257 @default.
- W3100553354 hasAuthorship W3100553354A5028197135 @default.
- W3100553354 hasAuthorship W3100553354A5071329195 @default.
- W3100553354 hasBestOaLocation W31005533541 @default.
- W3100553354 hasConcept C111030470 @default.
- W3100553354 hasConcept C119857082 @default.
- W3100553354 hasConcept C124101348 @default.
- W3100553354 hasConcept C127413603 @default.
- W3100553354 hasConcept C154945302 @default.
- W3100553354 hasConcept C21200559 @default.
- W3100553354 hasConcept C23130292 @default.
- W3100553354 hasConcept C24326235 @default.
- W3100553354 hasConcept C2522767166 @default.
- W3100553354 hasConcept C41008148 @default.
- W3100553354 hasConcept C79337645 @default.
- W3100553354 hasConceptScore W3100553354C111030470 @default.
- W3100553354 hasConceptScore W3100553354C119857082 @default.
- W3100553354 hasConceptScore W3100553354C124101348 @default.
- W3100553354 hasConceptScore W3100553354C127413603 @default.
- W3100553354 hasConceptScore W3100553354C154945302 @default.
- W3100553354 hasConceptScore W3100553354C21200559 @default.
- W3100553354 hasConceptScore W3100553354C23130292 @default.
- W3100553354 hasConceptScore W3100553354C24326235 @default.
- W3100553354 hasConceptScore W3100553354C2522767166 @default.
- W3100553354 hasConceptScore W3100553354C41008148 @default.
- W3100553354 hasConceptScore W3100553354C79337645 @default.
- W3100553354 hasIssue "1" @default.
- W3100553354 hasLocation W31005533541 @default.
- W3100553354 hasLocation W31005533542 @default.
- W3100553354 hasLocation W31005533543 @default.
- W3100553354 hasLocation W31005533544 @default.
- W3100553354 hasLocation W31005533545 @default.
- W3100553354 hasLocation W31005533546 @default.
- W3100553354 hasLocation W31005533547 @default.
- W3100553354 hasOpenAccess W3100553354 @default.
- W3100553354 hasPrimaryLocation W31005533541 @default.
- W3100553354 hasRelatedWork W1751413323 @default.
- W3100553354 hasRelatedWork W2315671126 @default.
- W3100553354 hasRelatedWork W2558166297 @default.
- W3100553354 hasRelatedWork W2571704763 @default.
- W3100553354 hasRelatedWork W2604501336 @default.
- W3100553354 hasRelatedWork W2734500670 @default.
- W3100553354 hasRelatedWork W2964481303 @default.
- W3100553354 hasRelatedWork W3038283795 @default.
- W3100553354 hasRelatedWork W3206394311 @default.
- W3100553354 hasRelatedWork W798507144 @default.
- W3100553354 hasVolume "13" @default.
- W3100553354 isParatext "false" @default.
- W3100553354 isRetracted "false" @default.
- W3100553354 magId "3100553354" @default.
- W3100553354 workType "article" @default.