mlsanityData to 7 Oct 2026

Time Series Forecasting via Semi-Asymmetric Convolutional Architecture with Global Atrous Sliding Window

arXiv 2301.13691 ↗First posted 31 Jan 2023cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

The proposed method in this paper is designed to address the problem of time series forecasting. Although some exquisitely designed models achieve excellent prediction performances, how to extract more useful information and make accurate predictions is still an open issue. Most of modern models only focus on a short range of information, which are fatal for problems such as time series forecasting which needs to capture long-term information characteristics. As a result, the main concern of this work is to further mine relationship between local and global information contained in time series to produce more precise predictions. In this paper, to satisfactorily realize the purpose, we make three main contributions that are experimentally verified to have performance advantages. Firstly, original time series is transformed into difference sequence which serves as input to the proposed model. And secondly, we introduce the global atrous sliding window into the forecasting model which references the concept of fuzzy time series to associate relevant global information with temporal data within a time period and utilizes central-bidirectional atrous algorithm to capture underlying-related features to ensure validity and consistency of captured data. Thirdly, a variation of widely-used asymmetric convolution which is called semi-asymmetric convolution is devised to more flexibly extract relationships in adjacent elements and corresponding associated global features with adjustable ranges of convolution on vertical and horizontal directions. The proposed model in this paper achieves state-of-the-art on most of time series datasets provided compared with competitive modern models.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 63 references that are in the map. First posted on arXiv 31 Jan 2023.

Builds on

29 of 63 references.

References · 29

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  3. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  4. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  5. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  6. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  7. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  8. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  9. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 744
  10. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 552
  11. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  12. 2014Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluationcited by 304
17 more
  1. 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
  2. 2014Speeding up Convolutional Neural Networks with Low Rank Expansionscited by 283
  3. 2021Monash Time Series Forecasting Archivecited by 256
  4. 2021AutoFormer: Searching Transformers for Visual Recognitioncited by 186
  5. 2019ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blockscited by 178
  6. 2017Conditional Time Series Forecasting with Convolutional Neural Networkscited by 121
  7. 2022Learning the Evolutionary and Multi-scale Graph Structure for Multivariate Time Series Forecastingcited by 36
  8. 2018Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentationcited by 26
  9. 2019LSTM-MSNet: Leveraging Forecasts on Sets of Related Time Series with Multiple Seasonal Patternscited by 23
  10. 2014Flattened Convolutional Neural Networks for Feedforward Accelerationcited by 20
  11. 2019DSTP-RNN: a dual-stage two-phase attention-based recurrent neural networks for long-term and multivariate time series predictioncited by 20
  12. 2021Deep Time Series Forecasting with Shape and Temporal Criteriacited by 10
  13. 2021Time Series Forecasting via Learning Convolutionally Low-Rank Modelscited by 9
  14. 2021Learning Non-Stationary Time-Series with Dynamic Pattern Extractionscited by 7
  15. 2021Multi-Graph Convolutional-Recurrent Neural Network (MGC-RNN) for Short-Term Forecasting of Transit Passenger Flowcited by 4
  16. 2020MultiSegVA: Using Visual Analytics to Segment Biologging Time Series on Multiple Scalescited by 3
  17. 2019Modelling Segmented Cardiotocography Time-Series Signals Using One-Dimensional Convolutional Neural Networks for the Early Detection of Abnormal Birth Outcomescited by 2

Built on by

Not cited yet.