Matches in SemOpenAlex for { <https://semopenalex.org/work/W4360764598> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4360764598 abstract "Deep learning utilizing transformers has recently achieved a lot of success in many vital areas such as natural language processing, computer vision, anomaly detection, and recommendation systems, among many others. Among several merits of transformers, the ability to capture long-range temporal dependencies and interactions is desirable for time series forecasting, leading to its progress in various time series applications. In this paper, we build a transformer model for non-stationary time series. The problem is challenging yet crucially important. We present a novel framework for univariate time series representation learning based on the wavelet-based transformer encoder architecture and call it W-Transformer. The proposed W-Transformers utilize a maximal overlap discrete wavelet transformation (MODWT) to the time series data and build local transformers on the decomposed datasets to vividly capture the nonstationarity and long-range nonlinear dependencies in the time series. Evaluating our framework on several publicly available benchmark time series datasets from various domains and with diverse characteristics, we demonstrate that it performs, on average, significantly better than the baseline forecasters for long-term forecasting, even for datasets that consist of only a few hundred training samples." @default.
- W4360764598 created "2023-03-25" @default.
- W4360764598 creator A5012926469 @default.
- W4360764598 creator A5013928164 @default.
- W4360764598 creator A5034695554 @default.
- W4360764598 date "2022-12-01" @default.
- W4360764598 modified "2023-09-27" @default.
- W4360764598 title "W-Transformers: A Wavelet-based Transformer Framework for Univariate Time Series Forecasting" @default.
- W4360764598 cites W2034032998 @default.
- W4360764598 cites W2035876214 @default.
- W4360764598 cites W2036681246 @default.
- W4360764598 cites W2064675550 @default.
- W4360764598 cites W2067984959 @default.
- W4360764598 cites W2116512828 @default.
- W4360764598 cites W2145856394 @default.
- W4360764598 cites W2165170334 @default.
- W4360764598 cites W2903162817 @default.
- W4360764598 cites W2936479322 @default.
- W4360764598 cites W2952301058 @default.
- W4360764598 cites W2964199361 @default.
- W4360764598 cites W2971724044 @default.
- W4360764598 cites W2979826702 @default.
- W4360764598 cites W2980994438 @default.
- W4360764598 cites W3011590044 @default.
- W4360764598 cites W3022122691 @default.
- W4360764598 cites W3022643593 @default.
- W4360764598 cites W3111294584 @default.
- W4360764598 cites W3129433613 @default.
- W4360764598 cites W3188872815 @default.
- W4360764598 cites W3212024433 @default.
- W4360764598 cites W4206189171 @default.
- W4360764598 cites W4230410911 @default.
- W4360764598 cites W4241574976 @default.
- W4360764598 cites W4298352105 @default.
- W4360764598 doi "https://doi.org/10.1109/icmla55696.2022.00111" @default.
- W4360764598 hasPublicationYear "2022" @default.
- W4360764598 type Work @default.
- W4360764598 citedByCount "2" @default.
- W4360764598 countsByYear W43607645982023 @default.
- W4360764598 crossrefType "proceedings-article" @default.
- W4360764598 hasAuthorship W4360764598A5012926469 @default.
- W4360764598 hasAuthorship W4360764598A5013928164 @default.
- W4360764598 hasAuthorship W4360764598A5034695554 @default.
- W4360764598 hasBestOaLocation W43607645982 @default.
- W4360764598 hasConcept C119599485 @default.
- W4360764598 hasConcept C119857082 @default.
- W4360764598 hasConcept C124101348 @default.
- W4360764598 hasConcept C127413603 @default.
- W4360764598 hasConcept C151406439 @default.
- W4360764598 hasConcept C154945302 @default.
- W4360764598 hasConcept C161584116 @default.
- W4360764598 hasConcept C165801399 @default.
- W4360764598 hasConcept C196216189 @default.
- W4360764598 hasConcept C199163554 @default.
- W4360764598 hasConcept C41008148 @default.
- W4360764598 hasConcept C47432892 @default.
- W4360764598 hasConcept C66322947 @default.
- W4360764598 hasConceptScore W4360764598C119599485 @default.
- W4360764598 hasConceptScore W4360764598C119857082 @default.
- W4360764598 hasConceptScore W4360764598C124101348 @default.
- W4360764598 hasConceptScore W4360764598C127413603 @default.
- W4360764598 hasConceptScore W4360764598C151406439 @default.
- W4360764598 hasConceptScore W4360764598C154945302 @default.
- W4360764598 hasConceptScore W4360764598C161584116 @default.
- W4360764598 hasConceptScore W4360764598C165801399 @default.
- W4360764598 hasConceptScore W4360764598C196216189 @default.
- W4360764598 hasConceptScore W4360764598C199163554 @default.
- W4360764598 hasConceptScore W4360764598C41008148 @default.
- W4360764598 hasConceptScore W4360764598C47432892 @default.
- W4360764598 hasConceptScore W4360764598C66322947 @default.
- W4360764598 hasLocation W43607645981 @default.
- W4360764598 hasLocation W43607645982 @default.
- W4360764598 hasOpenAccess W4360764598 @default.
- W4360764598 hasPrimaryLocation W43607645981 @default.
- W4360764598 hasRelatedWork W1982117133 @default.
- W4360764598 hasRelatedWork W2027136079 @default.
- W4360764598 hasRelatedWork W2036450930 @default.
- W4360764598 hasRelatedWork W2072994493 @default.
- W4360764598 hasRelatedWork W2354804553 @default.
- W4360764598 hasRelatedWork W2789684973 @default.
- W4360764598 hasRelatedWork W3004526984 @default.
- W4360764598 hasRelatedWork W3043692960 @default.
- W4360764598 hasRelatedWork W4213225422 @default.
- W4360764598 hasRelatedWork W4309045103 @default.
- W4360764598 isParatext "false" @default.
- W4360764598 isRetracted "false" @default.
- W4360764598 workType "article" @default.