FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312864314> ?p ?o ?g. }

• W4312864314 abstract "Time series forecasting is an important problem involving many fields, including the prediction of extreme weather early warning, electricity consumption planning, and long-term traffic congestion. Compared with one-step-ahead prediction, multi-horizon forecasting demands high prediction capacity of the model. Recent studies have shown the great potential of Transformer to improve the prediction accuracy. However, there are three problems with Transformer that restrict its performance, i.e. error accumulation, short-term and long-term dependencies. First, due to the teacher forcing strategy, the ground truth of target values are given during training and replaced by previous step output during testing. This difference between training and testing can lead to error accumulation. Second, time series data have a strong dependence on their local time information. But in classical Transformer architecture, the dot-product self-attention is computed by point-wise values, which are insensitive to local context. Thus, they may fail to distinguish between a turning point, an outlier and the part of patterns. Third, most methods optimize only one objective function and don't model the distributions of data, which is difficult to capture the long-term intricate patterns of time series. To solve these issues, we propose a Transformer-based time series forecasting model in this paper, named Adversarial Convolutional Transformer(ACT). First, we change the decoding mode from step-by-step way to one-step way, which can predict the entire sequence at one forward step to relieve the error accumulation issue. Next, we propose the convolutional attention block, which incorporates local context into the self-attention mechanism and captures the short-term dependencies of data. Then, we introduce adversarial training to the model to capture the long-term repeating patterns. Experiments on five challenging datasets demonstrate that ACT can bring solid improvements in accuracy." @default.
• W4312864314 created "2023-01-05" @default.
• W4312864314 creator A5011656765 @default.
• W4312864314 creator A5020496314 @default.
• W4312864314 creator A5061838242 @default.
• W4312864314 creator A5076196391 @default.
• W4312864314 creator A5084870242 @default.
• W4312864314 date "2022-07-18" @default.
• W4312864314 modified "2023-10-06" @default.
• W4312864314 title "ACT: Adversarial Convolutional Transformer for Time Series Forecasting" @default.
• W4312864314 cites W2026430219 @default.
• W4312864314 cites W2064675550 @default.
• W4312864314 cites W2100718094 @default.
• W4312864314 cites W2604847698 @default.
• W4312864314 cites W2749165076 @default.
• W4312864314 cites W2794209590 @default.
• W4312864314 cites W2884001105 @default.
• W4312864314 cites W2949468773 @default.
• W4312864314 cites W2980994438 @default.
• W4312864314 cites W3022643593 @default.
• W4312864314 cites W3089687835 @default.
• W4312864314 cites W3177318507 @default.
• W4312864314 doi "https://doi.org/10.1109/ijcnn55064.2022.9892791" @default.
• W4312864314 hasPublicationYear "2022" @default.
• W4312864314 type Work @default.
• W4312864314 citedByCount "2" @default.
• W4312864314 countsByYear W43128643142023 @default.
• W4312864314 crossrefType "proceedings-article" @default.
• W4312864314 hasAuthorship W4312864314A5011656765 @default.
• W4312864314 hasAuthorship W4312864314A5020496314 @default.
• W4312864314 hasAuthorship W4312864314A5061838242 @default.
• W4312864314 hasAuthorship W4312864314A5076196391 @default.
• W4312864314 hasAuthorship W4312864314A5084870242 @default.
• W4312864314 hasConcept C11413529 @default.
• W4312864314 hasConcept C119599485 @default.
• W4312864314 hasConcept C119857082 @default.
• W4312864314 hasConcept C127413603 @default.
• W4312864314 hasConcept C154945302 @default.
• W4312864314 hasConcept C165801399 @default.
• W4312864314 hasConcept C41008148 @default.
• W4312864314 hasConcept C66322947 @default.
• W4312864314 hasConcept C79337645 @default.
• W4312864314 hasConceptScore W4312864314C11413529 @default.
• W4312864314 hasConceptScore W4312864314C119599485 @default.
• W4312864314 hasConceptScore W4312864314C119857082 @default.
• W4312864314 hasConceptScore W4312864314C127413603 @default.
• W4312864314 hasConceptScore W4312864314C154945302 @default.
• W4312864314 hasConceptScore W4312864314C165801399 @default.
• W4312864314 hasConceptScore W4312864314C41008148 @default.
• W4312864314 hasConceptScore W4312864314C66322947 @default.
• W4312864314 hasConceptScore W4312864314C79337645 @default.
• W4312864314 hasFunder F4320335777 @default.
• W4312864314 hasLocation W43128643141 @default.
• W4312864314 hasOpenAccess W4312864314 @default.
• W4312864314 hasPrimaryLocation W43128643141 @default.
• W4312864314 hasRelatedWork W2961085424 @default.
• W4312864314 hasRelatedWork W3046775127 @default.
• W4312864314 hasRelatedWork W3170094116 @default.
• W4312864314 hasRelatedWork W4205958290 @default.
• W4312864314 hasRelatedWork W4285260836 @default.
• W4312864314 hasRelatedWork W4286629047 @default.
• W4312864314 hasRelatedWork W4306321456 @default.
• W4312864314 hasRelatedWork W4306674287 @default.
• W4312864314 hasRelatedWork W4386462264 @default.
• W4312864314 hasRelatedWork W4224009465 @default.
• W4312864314 isParatext "false" @default.
• W4312864314 isRetracted "false" @default.
• W4312864314 workType "article" @default.