Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387156698> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4387156698 abstract "Multivariate time series (MTS) forecasting involves predicting future time series data based on historical observations. Existing research primarily emphasizes the development of complex spatial-temporal models that capture spatial dependencies and temporal correlations among time series variables explicitly. However, recent advances have been impeded by challenges relating to data scarcity and model robustness. To address these issues, we propose Spatial-Temporal Masked Autoencoders (STMAE), an MTS forecasting framework that leverages masked autoencoders to enhance the performance of spatial-temporal baseline models. STMAE consists of two learning stages. In the pretraining stage, an encoder-decoder architecture is employed. The encoder processes the partially visible MTS data produced by a novel dual-masking strategy, including biased random walk-based spatial masking and patch-based temporal masking. Subsequently, the decoders aim to reconstruct the masked counterparts from both spatial and temporal perspectives. The pretraining stage establishes a challenging pretext task, compelling the encoder to learn robust spatial-temporal patterns. In the fine-tuning stage, the pretrained encoder is retained, and the original decoder from existing spatial-temporal models is appended for forecasting. Extensive experiments are conducted on multiple MTS benchmarks. The promising results demonstrate that integrating STMAE into various spatial-temporal models can largely enhance their MTS forecasting capability." @default.
- W4387156698 created "2023-09-30" @default.
- W4387156698 creator A5011045620 @default.
- W4387156698 creator A5073739058 @default.
- W4387156698 creator A5075581701 @default.
- W4387156698 creator A5076699095 @default.
- W4387156698 creator A5088266408 @default.
- W4387156698 date "2023-09-26" @default.
- W4387156698 modified "2023-09-30" @default.
- W4387156698 title "Revealing the Power of Spatial-Temporal Masked Autoencoders in Multivariate Time Series Forecasting" @default.
- W4387156698 doi "https://doi.org/10.48550/arxiv.2309.15169" @default.
- W4387156698 hasPublicationYear "2023" @default.
- W4387156698 type Work @default.
- W4387156698 citedByCount "0" @default.
- W4387156698 crossrefType "posted-content" @default.
- W4387156698 hasAuthorship W4387156698A5011045620 @default.
- W4387156698 hasAuthorship W4387156698A5073739058 @default.
- W4387156698 hasAuthorship W4387156698A5075581701 @default.
- W4387156698 hasAuthorship W4387156698A5076699095 @default.
- W4387156698 hasAuthorship W4387156698A5088266408 @default.
- W4387156698 hasBestOaLocation W43871566981 @default.
- W4387156698 hasConcept C104317684 @default.
- W4387156698 hasConcept C105795698 @default.
- W4387156698 hasConcept C111919701 @default.
- W4387156698 hasConcept C118505674 @default.
- W4387156698 hasConcept C119857082 @default.
- W4387156698 hasConcept C124101348 @default.
- W4387156698 hasConcept C142362112 @default.
- W4387156698 hasConcept C151406439 @default.
- W4387156698 hasConcept C153180895 @default.
- W4387156698 hasConcept C153349607 @default.
- W4387156698 hasConcept C154945302 @default.
- W4387156698 hasConcept C159620131 @default.
- W4387156698 hasConcept C161584116 @default.
- W4387156698 hasConcept C185592680 @default.
- W4387156698 hasConcept C2777402240 @default.
- W4387156698 hasConcept C33923547 @default.
- W4387156698 hasConcept C41008148 @default.
- W4387156698 hasConcept C55493867 @default.
- W4387156698 hasConcept C63479239 @default.
- W4387156698 hasConcept C77277458 @default.
- W4387156698 hasConceptScore W4387156698C104317684 @default.
- W4387156698 hasConceptScore W4387156698C105795698 @default.
- W4387156698 hasConceptScore W4387156698C111919701 @default.
- W4387156698 hasConceptScore W4387156698C118505674 @default.
- W4387156698 hasConceptScore W4387156698C119857082 @default.
- W4387156698 hasConceptScore W4387156698C124101348 @default.
- W4387156698 hasConceptScore W4387156698C142362112 @default.
- W4387156698 hasConceptScore W4387156698C151406439 @default.
- W4387156698 hasConceptScore W4387156698C153180895 @default.
- W4387156698 hasConceptScore W4387156698C153349607 @default.
- W4387156698 hasConceptScore W4387156698C154945302 @default.
- W4387156698 hasConceptScore W4387156698C159620131 @default.
- W4387156698 hasConceptScore W4387156698C161584116 @default.
- W4387156698 hasConceptScore W4387156698C185592680 @default.
- W4387156698 hasConceptScore W4387156698C2777402240 @default.
- W4387156698 hasConceptScore W4387156698C33923547 @default.
- W4387156698 hasConceptScore W4387156698C41008148 @default.
- W4387156698 hasConceptScore W4387156698C55493867 @default.
- W4387156698 hasConceptScore W4387156698C63479239 @default.
- W4387156698 hasConceptScore W4387156698C77277458 @default.
- W4387156698 hasLocation W43871566981 @default.
- W4387156698 hasOpenAccess W4387156698 @default.
- W4387156698 hasPrimaryLocation W43871566981 @default.
- W4387156698 hasRelatedWork W1579351779 @default.
- W4387156698 hasRelatedWork W1583803624 @default.
- W4387156698 hasRelatedWork W2065827785 @default.
- W4387156698 hasRelatedWork W207353543 @default.
- W4387156698 hasRelatedWork W2119243322 @default.
- W4387156698 hasRelatedWork W2124552104 @default.
- W4387156698 hasRelatedWork W2354804553 @default.
- W4387156698 hasRelatedWork W24016361 @default.
- W4387156698 hasRelatedWork W4361011496 @default.
- W4387156698 hasRelatedWork W2166328384 @default.
- W4387156698 isParatext "false" @default.
- W4387156698 isRetracted "false" @default.
- W4387156698 workType "article" @default.