FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3007299160> ?p ?o ?g. }

• W3007299160 abstract "Deleting data from a trained machine learning (ML) model is a critical task in many applications. For example, we may want to remove the influence of training points that might be out of date or outliers. Regulations such as EU's General Data Protection Regulation also stipulate that individuals can request to have their data deleted. The naive approach to data deletion is to retrain the ML model on the remaining data, but this is too time consuming. Moreover there is no known efficient algorithm that exactly deletes data from most ML models. In this work, we evaluate several approaches for approximate data deletion from trained models. For the case of linear regression, we propose a new method with linear dependence on the feature dimension $d$, a significant gain over all existing methods which all have superlinear time dependence on the dimension. We also provide a new test for evaluating data deletion from linear models." @default.
• W3007299160 created "2020-03-06" @default.
• W3007299160 creator A5005779176 @default.
• W3007299160 creator A5010790447 @default.
• W3007299160 creator A5029431777 @default.
• W3007299160 creator A5082633158 @default.
• W3007299160 date "2020-02-24" @default.
• W3007299160 modified "2023-09-27" @default.
• W3007299160 title "Approximate Data Deletion from Machine Learning Models: Algorithms and Evaluations." @default.
• W3007299160 cites W1473189865 @default.
• W3007299160 cites W1488996941 @default.
• W3007299160 cites W1503398984 @default.
• W3007299160 cites W1598866093 @default.
• W3007299160 cites W1994567799 @default.
• W3007299160 cites W2091075671 @default.
• W3007299160 cites W2101234009 @default.
• W3007299160 cites W2108807072 @default.
• W3007299160 cites W2535690855 @default.
• W3007299160 cites W2899771611 @default.
• W3007299160 cites W2945693042 @default.
• W3007299160 cites W2946930197 @default.
• W3007299160 cites W2947285452 @default.
• W3007299160 cites W2947642149 @default.
• W3007299160 cites W2949565981 @default.
• W3007299160 cites W2961073278 @default.
• W3007299160 cites W2963378725 @default.
• W3007299160 cites W2963723885 @default.
• W3007299160 cites W3035616549 @default.
• W3007299160 cites W3118608800 @default.
• W3007299160 cites W3120740533 @default.
• W3007299160 hasPublicationYear "2020" @default.
• W3007299160 type Work @default.
• W3007299160 sameAs 3007299160 @default.
• W3007299160 citedByCount "11" @default.
• W3007299160 countsByYear W30072991602020 @default.
• W3007299160 countsByYear W30072991602021 @default.
• W3007299160 countsByYear W30072991602022 @default.
• W3007299160 crossrefType "posted-content" @default.
• W3007299160 hasAuthorship W3007299160A5005779176 @default.
• W3007299160 hasAuthorship W3007299160A5010790447 @default.
• W3007299160 hasAuthorship W3007299160A5029431777 @default.
• W3007299160 hasAuthorship W3007299160A5082633158 @default.
• W3007299160 hasConcept C11413529 @default.
• W3007299160 hasConcept C119857082 @default.
• W3007299160 hasConcept C124101348 @default.
• W3007299160 hasConcept C138885662 @default.
• W3007299160 hasConcept C154945302 @default.
• W3007299160 hasConcept C162324750 @default.
• W3007299160 hasConcept C163175372 @default.
• W3007299160 hasConcept C16910744 @default.
• W3007299160 hasConcept C187736073 @default.
• W3007299160 hasConcept C199360897 @default.
• W3007299160 hasConcept C202444582 @default.
• W3007299160 hasConcept C2776401178 @default.
• W3007299160 hasConcept C2780451532 @default.
• W3007299160 hasConcept C33676613 @default.
• W3007299160 hasConcept C33923547 @default.
• W3007299160 hasConcept C41008148 @default.
• W3007299160 hasConcept C41895202 @default.
• W3007299160 hasConcept C48921125 @default.
• W3007299160 hasConcept C51632099 @default.
• W3007299160 hasConcept C67186912 @default.
• W3007299160 hasConcept C77088390 @default.
• W3007299160 hasConcept C79337645 @default.
• W3007299160 hasConceptScore W3007299160C11413529 @default.
• W3007299160 hasConceptScore W3007299160C119857082 @default.
• W3007299160 hasConceptScore W3007299160C124101348 @default.
• W3007299160 hasConceptScore W3007299160C138885662 @default.
• W3007299160 hasConceptScore W3007299160C154945302 @default.
• W3007299160 hasConceptScore W3007299160C162324750 @default.
• W3007299160 hasConceptScore W3007299160C163175372 @default.
• W3007299160 hasConceptScore W3007299160C16910744 @default.
• W3007299160 hasConceptScore W3007299160C187736073 @default.
• W3007299160 hasConceptScore W3007299160C199360897 @default.
• W3007299160 hasConceptScore W3007299160C202444582 @default.
• W3007299160 hasConceptScore W3007299160C2776401178 @default.
• W3007299160 hasConceptScore W3007299160C2780451532 @default.
• W3007299160 hasConceptScore W3007299160C33676613 @default.
• W3007299160 hasConceptScore W3007299160C33923547 @default.
• W3007299160 hasConceptScore W3007299160C41008148 @default.
• W3007299160 hasConceptScore W3007299160C41895202 @default.
• W3007299160 hasConceptScore W3007299160C48921125 @default.
• W3007299160 hasConceptScore W3007299160C51632099 @default.
• W3007299160 hasConceptScore W3007299160C67186912 @default.
• W3007299160 hasConceptScore W3007299160C77088390 @default.
• W3007299160 hasConceptScore W3007299160C79337645 @default.
• W3007299160 hasLocation W30072991601 @default.
• W3007299160 hasOpenAccess W3007299160 @default.
• W3007299160 hasPrimaryLocation W30072991601 @default.
• W3007299160 hasRelatedWork W1488996941 @default.
• W3007299160 hasRelatedWork W1504988876 @default.
• W3007299160 hasRelatedWork W2027595342 @default.
• W3007299160 hasRelatedWork W2051267297 @default.
• W3007299160 hasRelatedWork W2246051543 @default.
• W3007299160 hasRelatedWork W2473418344 @default.
• W3007299160 hasRelatedWork W2535690855 @default.
• W3007299160 hasRelatedWork W2795435272 @default.
• W3007299160 hasRelatedWork W2910588064 @default.
• W3007299160 hasRelatedWork W2962711646 @default.
• W3007299160 hasRelatedWork W2963378725 @default.

• next