FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1488996941> ?p ?o ?g. }

• W1488996941 abstract "Today's systems produce a rapidly exploding amount of data, and the data further derives more data, forming a complex data propagation network that we call the data's lineage. There are many reasons that users want systems to forget certain data including its lineage. From a privacy perspective, users who become concerned with new privacy risks of a system often want the system to forget their data and lineage. From a security perspective, if an attacker pollutes an anomaly detector by injecting manually crafted data into the training data set, the detector must forget the injected data to regain security. From a usability perspective, a user can remove noise and incorrect entries so that a recommendation engine gives useful recommendations. Therefore, we envision forgetting systems, capable of forgetting certain data and their lineages, completely and quickly. This paper focuses on making learning systems forget, the process of which we call machine unlearning, or simply unlearning. We present a general, efficient unlearning approach by transforming learning algorithms used by a system into a summation form. To forget a training data sample, our approach simply updates a small number of summations -- asymptotically faster than retraining from scratch. Our approach is general, because the summation form is from the statistical query learning in which many machine learning algorithms can be implemented. Our approach also applies to all stages of machine learning, including feature selection and modeling. Our evaluation, on four diverse learning systems and real-world workloads, shows that our approach is general, effective, fast, and easy to use." @default.
• W1488996941 created "2016-06-24" @default.
• W1488996941 creator A5056288677 @default.
• W1488996941 creator A5070605476 @default.
• W1488996941 date "2015-05-01" @default.
• W1488996941 modified "2023-10-09" @default.
• W1488996941 title "Towards Making Systems Forget with Machine Unlearning" @default.
• W1488996941 cites W1581774316 @default.
• W1488996941 cites W1970088130 @default.
• W1488996941 cites W1988146703 @default.
• W1488996941 cites W1995897489 @default.
• W1488996941 cites W2022097286 @default.
• W1488996941 cites W2033368661 @default.
• W1488996941 cites W2038296020 @default.
• W1488996941 cites W2039524325 @default.
• W1488996941 cites W2042281163 @default.
• W1488996941 cites W2060114273 @default.
• W1488996941 cites W2064208261 @default.
• W1488996941 cites W2068714596 @default.
• W1488996941 cites W2082190528 @default.
• W1488996941 cites W2083570493 @default.
• W1488996941 cites W2087445078 @default.
• W1488996941 cites W2095577883 @default.
• W1488996941 cites W2100454174 @default.
• W1488996941 cites W2103154003 @default.
• W1488996941 cites W2112841646 @default.
• W1488996941 cites W2117406138 @default.
• W1488996941 cites W2119804197 @default.
• W1488996941 cites W2123147099 @default.
• W1488996941 cites W2125908420 @default.
• W1488996941 cites W2137786570 @default.
• W1488996941 cites W2141481372 @default.
• W1488996941 cites W2142144955 @default.
• W1488996941 cites W2152565070 @default.
• W1488996941 cites W2161351857 @default.
• W1488996941 cites W2162275200 @default.
• W1488996941 cites W2162379889 @default.
• W1488996941 cites W2611675901 @default.
• W1488996941 cites W3100570787 @default.
• W1488996941 cites W40229419 @default.
• W1488996941 cites W4236137412 @default.
• W1488996941 doi "https://doi.org/10.1109/sp.2015.35" @default.
• W1488996941 hasPublicationYear "2015" @default.
• W1488996941 type Work @default.
• W1488996941 sameAs 1488996941 @default.
• W1488996941 citedByCount "149" @default.
• W1488996941 countsByYear W14889969412016 @default.
• W1488996941 countsByYear W14889969412017 @default.
• W1488996941 countsByYear W14889969412018 @default.
• W1488996941 countsByYear W14889969412019 @default.
• W1488996941 countsByYear W14889969412020 @default.
• W1488996941 countsByYear W14889969412021 @default.
• W1488996941 countsByYear W14889969412022 @default.
• W1488996941 countsByYear W14889969412023 @default.
• W1488996941 crossrefType "proceedings-article" @default.
• W1488996941 hasAuthorship W1488996941A5056288677 @default.
• W1488996941 hasAuthorship W1488996941A5070605476 @default.
• W1488996941 hasBestOaLocation W14889969412 @default.
• W1488996941 hasConcept C107457646 @default.
• W1488996941 hasConcept C111919701 @default.
• W1488996941 hasConcept C119857082 @default.
• W1488996941 hasConcept C12713177 @default.
• W1488996941 hasConcept C138885662 @default.
• W1488996941 hasConcept C154945302 @default.
• W1488996941 hasConcept C199360897 @default.
• W1488996941 hasConcept C2778579508 @default.
• W1488996941 hasConcept C41008148 @default.
• W1488996941 hasConcept C41895202 @default.
• W1488996941 hasConcept C7149132 @default.
• W1488996941 hasConcept C98045186 @default.
• W1488996941 hasConceptScore W1488996941C107457646 @default.
• W1488996941 hasConceptScore W1488996941C111919701 @default.
• W1488996941 hasConceptScore W1488996941C119857082 @default.
• W1488996941 hasConceptScore W1488996941C12713177 @default.
• W1488996941 hasConceptScore W1488996941C138885662 @default.
• W1488996941 hasConceptScore W1488996941C154945302 @default.
• W1488996941 hasConceptScore W1488996941C199360897 @default.
• W1488996941 hasConceptScore W1488996941C2778579508 @default.
• W1488996941 hasConceptScore W1488996941C41008148 @default.
• W1488996941 hasConceptScore W1488996941C41895202 @default.
• W1488996941 hasConceptScore W1488996941C7149132 @default.
• W1488996941 hasConceptScore W1488996941C98045186 @default.
• W1488996941 hasLocation W14889969411 @default.
• W1488996941 hasLocation W14889969412 @default.
• W1488996941 hasOpenAccess W1488996941 @default.
• W1488996941 hasPrimaryLocation W14889969411 @default.
• W1488996941 hasRelatedWork W2961085424 @default.
• W1488996941 hasRelatedWork W3046775127 @default.
• W1488996941 hasRelatedWork W3170094116 @default.
• W1488996941 hasRelatedWork W3209574120 @default.
• W1488996941 hasRelatedWork W4205958290 @default.
• W1488996941 hasRelatedWork W4285260836 @default.
• W1488996941 hasRelatedWork W4286629047 @default.
• W1488996941 hasRelatedWork W4306321456 @default.
• W1488996941 hasRelatedWork W4306674287 @default.
• W1488996941 hasRelatedWork W4224009465 @default.
• W1488996941 isParatext "false" @default.
• W1488996941 isRetracted "false" @default.
• W1488996941 magId "1488996941" @default.
• W1488996941 workType "article" @default.