Timezone: »

FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting
Tian Zhou · Ziqing MA · xue wang · Qingsong Wen · Liang Sun · Tao Yao · Wotao Yin · Rong Jin

Tue Nov 29 02:00 PM -- 04:00 PM (PST) @ Hall J #641

Recent studies have shown that deep learning models such as RNNs and Transformers have brought significant performance gains for long-term forecasting of time series because they effectively utilize historical information. We found, however, that there is still great room for improvement in how to preserve historical information in neural networks while avoiding overfitting to noise present in the history. Addressing this allows better utilization of the capabilities of deep learning models. To this end, we design a \textbf{F}requency \textbf{i}improved \textbf{L}egendre \textbf{M}emory model, or {\bf FiLM}: it applies Legendre polynomial projections to approximate historical information, uses Fourier projection to remove noise, and adds a low-rank approximation to speed up computation. Our empirical studies show that the proposed FiLM significantly improves the accuracy of state-of-the-art models in multivariate and univariate long-term forecasting by (\textbf{19.2\%}, \textbf{22.6\%}), respectively. We also demonstrate that the representation module developed in this work can be used as a general plugin to improve the long-term prediction performance of other deep learning modules. Code is available at https://github.com/tianzhou2011/FiLM/.

Author Information

Tian Zhou (Alibaba Group)
Ziqing MA (Alibaba)
xue wang (Alibaba)
Qingsong Wen (Alibaba Group U.S. Inc.)

Dr. Qingsong Wen is a Staff Engineer / Team Leader at DAMO Academy-Decision Intelligence Lab, Alibaba Group (U.S.), working in the areas of intelligent time series analysis, data-driven intelligence decisions, machine learning, and signal processing. He received his M.S. and Ph.D. degrees in Electrical and Computer Engineering from Georgia Institute of Technology, Atlanta, USA. He has published over 40 top-ranked conference and journal papers, and won First Place in the 2022 ICASSP Grand Challenge (AIOps in Networks) Competition. He is an Associate Editor for Neurocomputing, Guest Editor for Pattern Recognition, Guest Editor for Applied Energy, and regularly served as an SPC/PC member of the major DM/ML/AI conferences including KDD, ICDM, AAAI, IJCAI, etc.

Liang Sun (Alibaba Group)
Tao Yao (Alibaba Group)
Wotao Yin (Alibaba Group US)
Rong Jin (Alibaba)

More from the Same Authors