Matches in SemOpenAlex for { <https://semopenalex.org/work/W3214697985> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3214697985 abstract "Federated learning, which solves the problem of data island by connecting multiple computational devices into a decentralized system, has become a promising paradigm for privacy-preserving machine learning. This paper studies vertical federated learning (VFL), which tackles the scenarios where collaborating organizations share the same set of users but disjoint features. Contemporary VFL methods are mainly used in static scenarios where the active party and the passive party have all the data from the beginning and will not change. However, the data in real life often changes dynamically. To alleviate this problem, we propose a new vertical federation learning method, DVFL, which adapts to dynamic data distribution changes through knowledge distillation. In DVFL, most of the computations are held locally to improve data security and model efficiency. Our extensive experimental results show that DVFL can not only obtain results close to existing VFL methods in static scenes, but also adapt to changes in data distribution in dynamic scenarios." @default.
- W3214697985 created "2021-11-22" @default.
- W3214697985 creator A5013217360 @default.
- W3214697985 creator A5087953918 @default.
- W3214697985 date "2021-11-05" @default.
- W3214697985 modified "2023-10-17" @default.
- W3214697985 title "DVFL: A Vertical Federated Learning Method for Dynamic Data" @default.
- W3214697985 cites W1933938106 @default.
- W3214697985 cites W2051381803 @default.
- W3214697985 cites W2057907879 @default.
- W3214697985 cites W2085988980 @default.
- W3214697985 cites W2121423622 @default.
- W3214697985 cites W2541884796 @default.
- W3214697985 cites W2701059868 @default.
- W3214697985 cites W2773194476 @default.
- W3214697985 cites W2793216106 @default.
- W3214697985 cites W2794624686 @default.
- W3214697985 cites W2914853145 @default.
- W3214697985 cites W3029558105 @default.
- W3214697985 cites W3080261024 @default.
- W3214697985 cites W3080832531 @default.
- W3214697985 cites W3100393648 @default.
- W3214697985 cites W3101860164 @default.
- W3214697985 cites W3108959943 @default.
- W3214697985 cites W3124293845 @default.
- W3214697985 cites W3175265339 @default.
- W3214697985 doi "https://doi.org/10.48550/arxiv.2111.03341" @default.
- W3214697985 hasPublicationYear "2021" @default.
- W3214697985 type Work @default.
- W3214697985 sameAs 3214697985 @default.
- W3214697985 citedByCount "0" @default.
- W3214697985 crossrefType "posted-content" @default.
- W3214697985 hasAuthorship W3214697985A5013217360 @default.
- W3214697985 hasAuthorship W3214697985A5087953918 @default.
- W3214697985 hasBestOaLocation W32146979851 @default.
- W3214697985 hasConcept C11413529 @default.
- W3214697985 hasConcept C114614502 @default.
- W3214697985 hasConcept C119857082 @default.
- W3214697985 hasConcept C120314980 @default.
- W3214697985 hasConcept C124101348 @default.
- W3214697985 hasConcept C154945302 @default.
- W3214697985 hasConcept C177264268 @default.
- W3214697985 hasConcept C199360897 @default.
- W3214697985 hasConcept C2992525071 @default.
- W3214697985 hasConcept C33923547 @default.
- W3214697985 hasConcept C41008148 @default.
- W3214697985 hasConcept C45340560 @default.
- W3214697985 hasConcept C45374587 @default.
- W3214697985 hasConcept C58489278 @default.
- W3214697985 hasConceptScore W3214697985C11413529 @default.
- W3214697985 hasConceptScore W3214697985C114614502 @default.
- W3214697985 hasConceptScore W3214697985C119857082 @default.
- W3214697985 hasConceptScore W3214697985C120314980 @default.
- W3214697985 hasConceptScore W3214697985C124101348 @default.
- W3214697985 hasConceptScore W3214697985C154945302 @default.
- W3214697985 hasConceptScore W3214697985C177264268 @default.
- W3214697985 hasConceptScore W3214697985C199360897 @default.
- W3214697985 hasConceptScore W3214697985C2992525071 @default.
- W3214697985 hasConceptScore W3214697985C33923547 @default.
- W3214697985 hasConceptScore W3214697985C41008148 @default.
- W3214697985 hasConceptScore W3214697985C45340560 @default.
- W3214697985 hasConceptScore W3214697985C45374587 @default.
- W3214697985 hasConceptScore W3214697985C58489278 @default.
- W3214697985 hasLocation W32146979851 @default.
- W3214697985 hasOpenAccess W3214697985 @default.
- W3214697985 hasPrimaryLocation W32146979851 @default.
- W3214697985 hasRelatedWork W1544019696 @default.
- W3214697985 hasRelatedWork W2078736197 @default.
- W3214697985 hasRelatedWork W2091018730 @default.
- W3214697985 hasRelatedWork W2250140425 @default.
- W3214697985 hasRelatedWork W2389064843 @default.
- W3214697985 hasRelatedWork W2734587838 @default.
- W3214697985 hasRelatedWork W2966207284 @default.
- W3214697985 hasRelatedWork W3123345447 @default.
- W3214697985 hasRelatedWork W4280583453 @default.
- W3214697985 hasRelatedWork W2805391225 @default.
- W3214697985 isParatext "false" @default.
- W3214697985 isRetracted "false" @default.
- W3214697985 magId "3214697985" @default.
- W3214697985 workType "article" @default.