Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384526447> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4384526447 abstract "<p>Multivariate time series generative models mainly focus on generating time series from complete data, while few works generate complete multivariate time series from incomplete data, which is challenging to capture the feature correlation and temporal dependence simultaneously, due to the missing features and time segments. Missing values disrupt the feature correlation and temporal dependence learned by existing models, which deteriorates the distribution of missing values, resulting in low utility of synthetic data. Moreover, these methods capture feature correlation and temporal dependence separately, causing the joint distribution deviation of feature and time dimensions, thus reducing the synthetic data fidelity. In this work, we present a conditional diffusion model TimeDiff to generate time series with high fidelity and utility. This method randomly masks possible missing values in observed data as condition to conduct self-supervised learning of the missing value distribution. Meanwhile, uniting the feature and time dimensions, a multi-dimension temporal-feature network is proposed to capture the correlation of time variation among features. Experiments on real-world time series datasets demonstrate that TimeDiff reaches state-of-the-art results for generating high-utility multivariate time series from incomplete data with up to 80% missing rates.</p>" @default.
- W4384526447 created "2023-07-18" @default.
- W4384526447 creator A5018023542 @default.
- W4384526447 creator A5020074265 @default.
- W4384526447 creator A5042890249 @default.
- W4384526447 creator A5059295456 @default.
- W4384526447 creator A5069772530 @default.
- W4384526447 creator A5070002058 @default.
- W4384526447 date "2023-07-17" @default.
- W4384526447 modified "2023-09-26" @default.
- W4384526447 title "Diffusion Models for Multivariate Time Series Generation with Missing Values" @default.
- W4384526447 doi "https://doi.org/10.36227/techrxiv.23674863" @default.
- W4384526447 hasPublicationYear "2023" @default.
- W4384526447 type Work @default.
- W4384526447 citedByCount "0" @default.
- W4384526447 crossrefType "posted-content" @default.
- W4384526447 hasAuthorship W4384526447A5018023542 @default.
- W4384526447 hasAuthorship W4384526447A5020074265 @default.
- W4384526447 hasAuthorship W4384526447A5042890249 @default.
- W4384526447 hasAuthorship W4384526447A5059295456 @default.
- W4384526447 hasAuthorship W4384526447A5069772530 @default.
- W4384526447 hasAuthorship W4384526447A5070002058 @default.
- W4384526447 hasBestOaLocation W43845264471 @default.
- W4384526447 hasConcept C119857082 @default.
- W4384526447 hasConcept C138885662 @default.
- W4384526447 hasConcept C143724316 @default.
- W4384526447 hasConcept C151406439 @default.
- W4384526447 hasConcept C151730666 @default.
- W4384526447 hasConcept C153180895 @default.
- W4384526447 hasConcept C154945302 @default.
- W4384526447 hasConcept C161584116 @default.
- W4384526447 hasConcept C2776401178 @default.
- W4384526447 hasConcept C41008148 @default.
- W4384526447 hasConcept C41895202 @default.
- W4384526447 hasConcept C86803240 @default.
- W4384526447 hasConcept C9357733 @default.
- W4384526447 hasConceptScore W4384526447C119857082 @default.
- W4384526447 hasConceptScore W4384526447C138885662 @default.
- W4384526447 hasConceptScore W4384526447C143724316 @default.
- W4384526447 hasConceptScore W4384526447C151406439 @default.
- W4384526447 hasConceptScore W4384526447C151730666 @default.
- W4384526447 hasConceptScore W4384526447C153180895 @default.
- W4384526447 hasConceptScore W4384526447C154945302 @default.
- W4384526447 hasConceptScore W4384526447C161584116 @default.
- W4384526447 hasConceptScore W4384526447C2776401178 @default.
- W4384526447 hasConceptScore W4384526447C41008148 @default.
- W4384526447 hasConceptScore W4384526447C41895202 @default.
- W4384526447 hasConceptScore W4384526447C86803240 @default.
- W4384526447 hasConceptScore W4384526447C9357733 @default.
- W4384526447 hasLocation W43845264471 @default.
- W4384526447 hasOpenAccess W4384526447 @default.
- W4384526447 hasPrimaryLocation W43845264471 @default.
- W4384526447 hasRelatedWork W189280425 @default.
- W4384526447 hasRelatedWork W2061542064 @default.
- W4384526447 hasRelatedWork W2066565491 @default.
- W4384526447 hasRelatedWork W2068251166 @default.
- W4384526447 hasRelatedWork W2382607599 @default.
- W4384526447 hasRelatedWork W2546942002 @default.
- W4384526447 hasRelatedWork W2885909555 @default.
- W4384526447 hasRelatedWork W2970216048 @default.
- W4384526447 hasRelatedWork W4285420330 @default.
- W4384526447 hasRelatedWork W3021842237 @default.
- W4384526447 isParatext "false" @default.
- W4384526447 isRetracted "false" @default.
- W4384526447 workType "article" @default.