FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3098480654> ?p ?o ?g. }

• W3098480654 abstract "Machine learning practitioners frequently seek to leverage the most informative available data, without violating the data owner's privacy, when building predictive models. Differentially private data synthesis protects personal details from exposure, and allows for the training of differentially private machine learning models on privately generated datasets. But how can we effectively assess the efficacy of differentially private synthetic data? In this paper, we survey four differentially private generative adversarial networks for data synthesis. We evaluate each of them at scale on five standard tabular datasets, and in two applied industry scenarios. We benchmark with novel metrics from recent literature and other standard machine learning tools. Our results suggest some synthesizers are more applicable for different privacy budgets, and we further demonstrate complicating domain-based tradeoffs in selecting an approach. We offer experimental learning on applied machine learning scenarios with private internal data to researchers and practitioners alike. In addition, we propose QUAIL, a two model hybrid approach to generating synthetic data. We examine QUAIL's tradeoffs, and note circumstances in which it outperforms baseline differentially private supervised learning models under the same budget constraint." @default.
• W3098480654 created "2020-11-23" @default.
• W3098480654 creator A5004349988 @default.
• W3098480654 creator A5008547275 @default.
• W3098480654 creator A5013117870 @default.
• W3098480654 creator A5066096821 @default.
• W3098480654 creator A5068868453 @default.
• W3098480654 creator A5084955278 @default.
• W3098480654 date "2021-05-04" @default.
• W3098480654 modified "2023-10-16" @default.
• W3098480654 title "Differentially Private Synthetic Data: Applied Evaluations and Enhancements" @default.
• W3098480654 cites W1873763122 @default.
• W3098480654 cites W1985310469 @default.
• W3098480654 cites W1993116423 @default.
• W3098480654 cites W2001238748 @default.
• W3098480654 cites W2027595342 @default.
• W3098480654 cites W2053637704 @default.
• W3098480654 cites W2070539708 @default.
• W3098480654 cites W2099471712 @default.
• W3098480654 cites W2101234009 @default.
• W3098480654 cites W2109426455 @default.
• W3098480654 cites W2119874464 @default.
• W3098480654 cites W2121727866 @default.
• W3098480654 cites W2170204206 @default.
• W3098480654 cites W2215385661 @default.
• W3098480654 cites W2217200224 @default.
• W3098480654 cites W2473418344 @default.
• W3098480654 cites W2591882872 @default.
• W3098480654 cites W2613416506 @default.
• W3098480654 cites W2729742878 @default.
• W3098480654 cites W2777683003 @default.
• W3098480654 cites W2781500801 @default.
• W3098480654 cites W2787711783 @default.
• W3098480654 cites W2789226849 @default.
• W3098480654 cites W2791094827 @default.
• W3098480654 cites W2794511224 @default.
• W3098480654 cites W2806276686 @default.
• W3098480654 cites W2810397096 @default.
• W3098480654 cites W2887995258 @default.
• W3098480654 cites W2908109788 @default.
• W3098480654 cites W2915946102 @default.
• W3098480654 cites W2942094298 @default.
• W3098480654 cites W2944996955 @default.
• W3098480654 cites W2950602864 @default.
• W3098480654 cites W2953120443 @default.
• W3098480654 cites W2954395498 @default.
• W3098480654 cites W2963559079 @default.
• W3098480654 cites W2963873275 @default.
• W3098480654 cites W2964296660 @default.
• W3098480654 cites W2967880504 @default.
• W3098480654 cites W2967985550 @default.
• W3098480654 cites W2971154760 @default.
• W3098480654 cites W2972280210 @default.
• W3098480654 cites W2997274846 @default.
• W3098480654 cites W3017044880 @default.
• W3098480654 cites W3028816787 @default.
• W3098480654 cites W3041137100 @default.
• W3098480654 cites W3071470454 @default.
• W3098480654 cites W3120740533 @default.
• W3098480654 cites W3141494665 @default.
• W3098480654 hasPublicationYear "2021" @default.
• W3098480654 type Work @default.
• W3098480654 sameAs 3098480654 @default.
• W3098480654 citedByCount "3" @default.
• W3098480654 countsByYear W30984806542020 @default.
• W3098480654 countsByYear W30984806542021 @default.
• W3098480654 crossrefType "journal-article" @default.
• W3098480654 hasAuthorship W3098480654A5004349988 @default.
• W3098480654 hasAuthorship W3098480654A5008547275 @default.
• W3098480654 hasAuthorship W3098480654A5013117870 @default.
• W3098480654 hasAuthorship W3098480654A5066096821 @default.
• W3098480654 hasAuthorship W3098480654A5068868453 @default.
• W3098480654 hasAuthorship W3098480654A5084955278 @default.
• W3098480654 hasConcept C111368507 @default.
• W3098480654 hasConcept C119857082 @default.
• W3098480654 hasConcept C124101348 @default.
• W3098480654 hasConcept C12725497 @default.
• W3098480654 hasConcept C127313418 @default.
• W3098480654 hasConcept C13280743 @default.
• W3098480654 hasConcept C134306372 @default.
• W3098480654 hasConcept C153083717 @default.
• W3098480654 hasConcept C154945302 @default.
• W3098480654 hasConcept C160920958 @default.
• W3098480654 hasConcept C167966045 @default.
• W3098480654 hasConcept C185798385 @default.
• W3098480654 hasConcept C205649164 @default.
• W3098480654 hasConcept C33923547 @default.
• W3098480654 hasConcept C36503486 @default.
• W3098480654 hasConcept C37736160 @default.
• W3098480654 hasConcept C39890363 @default.
• W3098480654 hasConcept C41008148 @default.
• W3098480654 hasConceptScore W3098480654C111368507 @default.
• W3098480654 hasConceptScore W3098480654C119857082 @default.
• W3098480654 hasConceptScore W3098480654C124101348 @default.
• W3098480654 hasConceptScore W3098480654C12725497 @default.
• W3098480654 hasConceptScore W3098480654C127313418 @default.
• W3098480654 hasConceptScore W3098480654C13280743 @default.
• W3098480654 hasConceptScore W3098480654C134306372 @default.
• W3098480654 hasConceptScore W3098480654C153083717 @default.
• W3098480654 hasConceptScore W3098480654C154945302 @default.

• next