FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3049087496> ?p ?o ?g. }

• W3049087496 abstract "In a lot of real-world data mining and machine learning applications, data are provided by multiple providers and each maintains private records of different feature sets about common entities. It is challenging to train these vertically partitioned data effectively and efficiently while keeping data privacy for traditional data mining and machine learning algorithms. In this paper, we focus on nonlinear learning with kernels, and propose a federated doubly stochastic kernel learning (FDSKL) algorithm for vertically partitioned data. Specifically, we use random features to approximate the kernel mapping function and use doubly stochastic gradients to update the solutions, which are all computed federatedly without the disclosure of data. Importantly, we prove that FDSKL has a sublinear convergence rate, and can guarantee the data security under the semi-honest assumption. Extensive experimental results on a variety of benchmark datasets show that FDSKL is significantly faster than state-of-the-art federated learning methods when dealing with kernels, while retaining the similar generalization performance." @default.
• W3049087496 created "2020-08-21" @default.
• W3049087496 creator A5021105768 @default.
• W3049087496 creator A5055404586 @default.
• W3049087496 creator A5060016795 @default.
• W3049087496 creator A5069728539 @default.
• W3049087496 date "2020-08-14" @default.
• W3049087496 modified "2023-10-17" @default.
• W3049087496 title "Federated Doubly Stochastic Kernel Learning for Vertically Partitioned Data" @default.
• W3049087496 cites W1484769234 @default.
• W3049087496 cites W1488526968 @default.
• W3049087496 cites W1565176583 @default.
• W3049087496 cites W1580095995 @default.
• W3049087496 cites W1838099784 @default.
• W3049087496 cites W1968265138 @default.
• W3049087496 cites W1988813039 @default.
• W3049087496 cites W2001032894 @default.
• W3049087496 cites W2041416246 @default.
• W3049087496 cites W2073821686 @default.
• W3049087496 cites W2093367651 @default.
• W3049087496 cites W2112340198 @default.
• W3049087496 cites W2123395972 @default.
• W3049087496 cites W2125085449 @default.
• W3049087496 cites W2138243089 @default.
• W3049087496 cites W2139336600 @default.
• W3049087496 cites W2142809864 @default.
• W3049087496 cites W2144902422 @default.
• W3049087496 cites W2145763471 @default.
• W3049087496 cites W2153635508 @default.
• W3049087496 cites W2773194476 @default.
• W3049087496 cites W2786051283 @default.
• W3049087496 cites W2789149658 @default.
• W3049087496 cites W2793216106 @default.
• W3049087496 cites W2798899619 @default.
• W3049087496 cites W2808552550 @default.
• W3049087496 cites W2809245559 @default.
• W3049087496 cites W2905265212 @default.
• W3049087496 cites W2914853145 @default.
• W3049087496 cites W2951781666 @default.
• W3049087496 cites W2964594890 @default.
• W3049087496 cites W2965180428 @default.
• W3049087496 cites W2997060212 @default.
• W3049087496 cites W3029558105 @default.
• W3049087496 doi "https://doi.org/10.48550/arxiv.2008.06197" @default.
• W3049087496 hasPublicationYear "2020" @default.
• W3049087496 type Work @default.
• W3049087496 sameAs 3049087496 @default.
• W3049087496 citedByCount "0" @default.
• W3049087496 crossrefType "posted-content" @default.
• W3049087496 hasAuthorship W3049087496A5021105768 @default.
• W3049087496 hasAuthorship W3049087496A5055404586 @default.
• W3049087496 hasAuthorship W3049087496A5060016795 @default.
• W3049087496 hasAuthorship W3049087496A5069728539 @default.
• W3049087496 hasBestOaLocation W30490874961 @default.
• W3049087496 hasConcept C114614502 @default.
• W3049087496 hasConcept C117160843 @default.
• W3049087496 hasConcept C119857082 @default.
• W3049087496 hasConcept C120665830 @default.
• W3049087496 hasConcept C121332964 @default.
• W3049087496 hasConcept C122280245 @default.
• W3049087496 hasConcept C12267149 @default.
• W3049087496 hasConcept C124101348 @default.
• W3049087496 hasConcept C13280743 @default.
• W3049087496 hasConcept C134306372 @default.
• W3049087496 hasConcept C136197465 @default.
• W3049087496 hasConcept C138885662 @default.
• W3049087496 hasConcept C154945302 @default.
• W3049087496 hasConcept C162324750 @default.
• W3049087496 hasConcept C177148314 @default.
• W3049087496 hasConcept C185798385 @default.
• W3049087496 hasConcept C192209626 @default.
• W3049087496 hasConcept C205649164 @default.
• W3049087496 hasConcept C2776401178 @default.
• W3049087496 hasConcept C2777303404 @default.
• W3049087496 hasConcept C33923547 @default.
• W3049087496 hasConcept C41008148 @default.
• W3049087496 hasConcept C41895202 @default.
• W3049087496 hasConcept C50522688 @default.
• W3049087496 hasConcept C74193536 @default.
• W3049087496 hasConceptScore W3049087496C114614502 @default.
• W3049087496 hasConceptScore W3049087496C117160843 @default.
• W3049087496 hasConceptScore W3049087496C119857082 @default.
• W3049087496 hasConceptScore W3049087496C120665830 @default.
• W3049087496 hasConceptScore W3049087496C121332964 @default.
• W3049087496 hasConceptScore W3049087496C122280245 @default.
• W3049087496 hasConceptScore W3049087496C12267149 @default.
• W3049087496 hasConceptScore W3049087496C124101348 @default.
• W3049087496 hasConceptScore W3049087496C13280743 @default.
• W3049087496 hasConceptScore W3049087496C134306372 @default.
• W3049087496 hasConceptScore W3049087496C136197465 @default.
• W3049087496 hasConceptScore W3049087496C138885662 @default.
• W3049087496 hasConceptScore W3049087496C154945302 @default.
• W3049087496 hasConceptScore W3049087496C162324750 @default.
• W3049087496 hasConceptScore W3049087496C177148314 @default.
• W3049087496 hasConceptScore W3049087496C185798385 @default.
• W3049087496 hasConceptScore W3049087496C192209626 @default.
• W3049087496 hasConceptScore W3049087496C205649164 @default.
• W3049087496 hasConceptScore W3049087496C2776401178 @default.
• W3049087496 hasConceptScore W3049087496C2777303404 @default.
• W3049087496 hasConceptScore W3049087496C33923547 @default.

• next