Matches in SemOpenAlex for { <https://semopenalex.org/work/W3049454350> ?p ?o ?g. }
- W3049454350 abstract "The privacy-preserving federated learning for vertically partitioned data has shown promising results as the solution of the emerging multi-party joint modeling application, in which the data holders (such as government branches, private finance and e-business companies) collaborate throughout the learning process rather than relying on a trusted third party to hold data. However, existing federated learning algorithms for vertically partitioned data are limited to synchronous computation. To improve the efficiency when the unbalanced computation/communication resources are common among the parties in the federated learning system, it is essential to develop asynchronous training algorithms for vertically partitioned data while keeping the data privacy. In this paper, we propose an asynchronous federated SGD (AFSGD-VP) algorithm and its SVRG and SAGA variants on the vertically partitioned data. Moreover, we provide the convergence analyses of AFSGD-VP and its SVRG and SAGA variants under the condition of strong convexity. We also discuss their model privacy, data privacy, computational complexities and communication costs. To the best of our knowledge, AFSGD-VP and its SVRG and SAGA variants are the first asynchronous federated learning algorithms for vertically partitioned data. Extensive experimental results on a variety of vertically partitioned datasets not only verify the theoretical results of AFSGD-VP and its SVRG and SAGA variants, but also show that our algorithms have much higher efficiency than the corresponding synchronous algorithms." @default.
- W3049454350 created "2020-08-21" @default.
- W3049454350 creator A5015874725 @default.
- W3049454350 creator A5060016795 @default.
- W3049454350 creator A5063099787 @default.
- W3049454350 creator A5069728539 @default.
- W3049454350 creator A5069872293 @default.
- W3049454350 date "2020-08-14" @default.
- W3049454350 modified "2023-10-16" @default.
- W3049454350 title "Privacy-Preserving Asynchronous Federated Learning Algorithms for Multi-Party Vertically Collaborative Learning." @default.
- W3049454350 cites W114517082 @default.
- W3049454350 cites W1484769234 @default.
- W3049454350 cites W1488526968 @default.
- W3049454350 cites W1596717185 @default.
- W3049454350 cites W1902354325 @default.
- W3049454350 cites W1968265138 @default.
- W3049454350 cites W2023901033 @default.
- W3049454350 cites W2041416246 @default.
- W3049454350 cites W2047152541 @default.
- W3049454350 cites W2093367651 @default.
- W3049454350 cites W2095984592 @default.
- W3049454350 cites W2112340198 @default.
- W3049454350 cites W2131174347 @default.
- W3049454350 cites W2135482703 @default.
- W3049454350 cites W2139336600 @default.
- W3049454350 cites W2153635508 @default.
- W3049454350 cites W2158547433 @default.
- W3049454350 cites W2412589610 @default.
- W3049454350 cites W2513289469 @default.
- W3049454350 cites W2525160011 @default.
- W3049454350 cites W2619493178 @default.
- W3049454350 cites W2626172370 @default.
- W3049454350 cites W2773194476 @default.
- W3049454350 cites W2786051283 @default.
- W3049454350 cites W2789149658 @default.
- W3049454350 cites W2793216106 @default.
- W3049454350 cites W2798899619 @default.
- W3049454350 cites W2804045096 @default.
- W3049454350 cites W2905265212 @default.
- W3049454350 cites W2912213068 @default.
- W3049454350 cites W2914853145 @default.
- W3049454350 cites W2947136928 @default.
- W3049454350 cites W2962952793 @default.
- W3049454350 cites W2963108795 @default.
- W3049454350 cites W2963139509 @default.
- W3049454350 cites W2963156201 @default.
- W3049454350 cites W2963373778 @default.
- W3049454350 cites W2963829227 @default.
- W3049454350 cites W2964113612 @default.
- W3049454350 cites W2964255842 @default.
- W3049454350 cites W3029558105 @default.
- W3049454350 cites W3039770199 @default.
- W3049454350 cites W3040963243 @default.
- W3049454350 cites W3125356412 @default.
- W3049454350 cites W2963821730 @default.
- W3049454350 hasPublicationYear "2020" @default.
- W3049454350 type Work @default.
- W3049454350 sameAs 3049454350 @default.
- W3049454350 citedByCount "8" @default.
- W3049454350 countsByYear W30494543502021 @default.
- W3049454350 crossrefType "posted-content" @default.
- W3049454350 hasAuthorship W3049454350A5015874725 @default.
- W3049454350 hasAuthorship W3049454350A5060016795 @default.
- W3049454350 hasAuthorship W3049454350A5063099787 @default.
- W3049454350 hasAuthorship W3049454350A5069728539 @default.
- W3049454350 hasAuthorship W3049454350A5069872293 @default.
- W3049454350 hasConcept C11413529 @default.
- W3049454350 hasConcept C119857082 @default.
- W3049454350 hasConcept C123201435 @default.
- W3049454350 hasConcept C124101348 @default.
- W3049454350 hasConcept C139089976 @default.
- W3049454350 hasConcept C151319957 @default.
- W3049454350 hasConcept C154945302 @default.
- W3049454350 hasConcept C162324750 @default.
- W3049454350 hasConcept C17744445 @default.
- W3049454350 hasConcept C19122763 @default.
- W3049454350 hasConcept C199539241 @default.
- W3049454350 hasConcept C2777072894 @default.
- W3049454350 hasConcept C2777303404 @default.
- W3049454350 hasConcept C2992525071 @default.
- W3049454350 hasConcept C31258907 @default.
- W3049454350 hasConcept C38652104 @default.
- W3049454350 hasConcept C41008148 @default.
- W3049454350 hasConcept C45374587 @default.
- W3049454350 hasConcept C50522688 @default.
- W3049454350 hasConcept C51672120 @default.
- W3049454350 hasConcept C75684735 @default.
- W3049454350 hasConcept C88610354 @default.
- W3049454350 hasConceptScore W3049454350C11413529 @default.
- W3049454350 hasConceptScore W3049454350C119857082 @default.
- W3049454350 hasConceptScore W3049454350C123201435 @default.
- W3049454350 hasConceptScore W3049454350C124101348 @default.
- W3049454350 hasConceptScore W3049454350C139089976 @default.
- W3049454350 hasConceptScore W3049454350C151319957 @default.
- W3049454350 hasConceptScore W3049454350C154945302 @default.
- W3049454350 hasConceptScore W3049454350C162324750 @default.
- W3049454350 hasConceptScore W3049454350C17744445 @default.
- W3049454350 hasConceptScore W3049454350C19122763 @default.
- W3049454350 hasConceptScore W3049454350C199539241 @default.
- W3049454350 hasConceptScore W3049454350C2777072894 @default.