Abstract
Time series forecasting (TSF) is crucial in many real-world applications. This paper studies the long-term forecasting problem of time series. Recent research has demonstrated that Transformer-based forecasting models can enhance forecasting accuracy, but their computational demands present a significant challenge for Long Sequence Time-series Forecasting (LSTF). To mitigate this, some researchers propose using a sparse attention network to reduce computational costs, but this approach can result in low information utilization and hinder long-term forecasting performance. This limitation impacts the overall effectiveness of the forecasting model. To address this issue, a new approach called Double-layer Efficient ProbSparse self-attention (DEPformer) is proposed in this paper for Long Sequence Time-series Forecasting. It combines a sparse attention network with an attention network that extracts global context vectors. This approach improves upon the low information utilization of sparse attention alone and enhances long-term forecasting performance. Experiments using standard and real datasets show that DEPformer outperforms the previous mainstream models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Box, G.E., Jenkins, G.M.: Some recent advances in forecasting and control. J. Roy. Stat. Soc. Ser. C (Appl. Stat.) 17(2), 91–109 (1968)
Smola, A.J., Schölkopf, B.: A tutorial on support vector regression. Stat. Comput. 14, 199–222 (2004)
Holt, C.C.: Forecasting seasonals and trends by exponentially weighted moving averages. Int. J. Forecast. 20(1), 5–10 (2004)
Box, G.E., Jenkins, G.M.: Time Series Analysis: Forecasting and Control. Holden-Day, San Francisco (1976)
Gardner, E.S., Jr.: Exponential smoothing: the state of the art. J. Forecast. 4(1), 1–28 (1985)
Winters, P.R.: Forecasting sales by exponentially weighted moving averages. Manag. Sci. 6(3), 324–342 (1960)
Ahmed, N.K., Atiya, A.F., Gayar, N.E., El-Shishiny, H.: An empirical comparison of machine learning models for time series forecasting. Econ. Rev. 29(5–6), 594–621 (2010)
Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., Zhang, W.: Informer: beyond efficient transformer for long sequence time-series forecasting. In: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, 2–9 February 2021, pp. 11106–11115. AAAI Press (2021). https://ojs.aaai.org/index.php/AAAI/article/view/17325
Box, G.E., Jenkins, G.M., Reinsel, G.C., Ljung, G.M.: Time Series Analysis: Forecasting and Control. John Wiley & Sons, Hoboken (2015)
Ray, W.: Time Series: Theory and Methods (1990)
Wen, R., Torkkola, K., Narayanaswamy, B., Madeka, D.: A multi-horizon quantile recurrent forecaster (2017). arXiv preprint arXiv:1711.11053
Rangapuram, S.S., Seeger, M.W., Gasthaus, J., Stella, L., Wang, Y., Januschowski, T.: Deep state space models for time series forecasting. Adv. Neural Inf. Process. Syst. 31, 1–10 (2018)
Yu, R., Zheng, S., Anandkumar, A., Yue, Y.: Long-term forecasting using higher order tensor rnns (2017). arXiv preprint arXiv:1711.00073
Maddix, D.C., Wang, Y., Smola, A.: Deep factors with gaussian processes for forecasting (2018). arXiv preprint arXiv:1812.00098
Salinas, D., Flunkert, V., Gasthaus, J., Januschowski, T.: Deepar: probabilistic forecasting with autoregressive recurrent networks. Int. J. Forecast. 36(3), 1181–1191 (2020)
Lai, G., Chang, W.C., Yang, Y., Liu, H.: Modeling long-and short-term temporal patterns with deep neural networks. In: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 95–104 (2018)
Qin, Y., Song, D., Chen, H., Cheng, W., Jiang, G., Cottrell, G.: A dual-stage attention-based recurrent neural network for time series prediction (2017). arXiv preprint arXiv:1704.02971
Shih, S.Y., Sun, F.K., Lee, H.Y.: Temporal pattern attention for multivariate time series forecasting. Mach. Learn. 108, 1421–1441 (2019)
Song, H., Rajan, D., Thiagarajan, J., Spanias, A.: Attend and diagnose: clinical time series analysis using attention models. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)
Borovykh, A., Bohte, S., Oosterlee, C.W.: Conditional time series forecasting with convolutional neural networks (2017). arXiv preprint arXiv:1703.04691
Bai, S., Kolter, J.Z., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling (2018). arXiv preprint arXiv:1803.01271
Sen, R., Yu, H.F., Dhillon, I.S.: Think globally, act locally: a deep neural network approach to high-dimensional time series forecasting. Adv. Neural Inf. Process. Syst. 32, 1–10 (2019)
Li, S., et al.: Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting. Adv. Neural Inf. Process. Syst. 32, 1–11 (2019)
Shen, Z., Zhang, M., Zhao, H., Yi, S., Li, H.: Efficient attention: attention with linear complexities. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 3531–3539 (2021)
Kitaev, N., Kaiser, Ł., Levskaya, A.: Reformer: the efficient transformer (2020). arXiv preprint arXiv:2001.04451
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate (2014). arXiv preprint arXiv:1409.0473
Taylor, S.J., Letham, B.: Forecasting at scale. Am. Stat. 72(1), 37–45 (2018)
Ariyo, A.A., Adewumi, A.O., Ayo, C.K.: Stock price prediction using the arima model. In: 2014 UKSim-AMSS 16th International Conference on Computer Modelling and Simulation, pp. 106–112. IEEE (2014)
Acknowledgments
This work is supported by “Tianjin Project + Team" Key Training Project under Grant No. XC202022
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ma, J., Wang, X., Xiao, Y. (2023). Double-Layer Attention for Long Sequence Time-Series Forecasting. In: Strauss, C., Amagasa, T., Kotsis, G., Tjoa, A.M., Khalil, I. (eds) Database and Expert Systems Applications. DEXA 2023. Lecture Notes in Computer Science, vol 14147. Springer, Cham. https://doi.org/10.1007/978-3-031-39821-6_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-39821-6_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-39820-9
Online ISBN: 978-3-031-39821-6
eBook Packages: Computer ScienceComputer Science (R0)