FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting

Abstract

Although Transformer-based methods have significantly improved state-of-the-art results for long-term series forecasting, they are not only computationally expensive but more importantly, are unable to capture the global view of time series (e.g. overall trend). To address these problems, we propose to combine Transformer with the seasonal-trend decomposition method, in which the decomposition method captures the global profile of time series while Transformers capture more detailed structures. To further enhance the performance of Transformer for long-term prediction, we exploit the fact that most time series tend to have a sparse representation in well-known basis such as Fourier transform, and develop a frequency enhanced Transformer. Besides being more effective, the proposed method, termed as Frequency Enhanced Decomposed Transformer ({\bf FEDformer}), is more efficient than standard Transformer with a linear complexity to the sequence length. Our empirical studies with six benchmark datasets show that compared with state-of-the-art methods, FEDformer can reduce prediction error by $14.8\%$ and $22.6\%$ for multivariate and univariate time series, respectively. Code is publicly available at https://github.com/MAZiqing/FEDformer.

Accepted by The 39th International Conference on Machine Learning (ICML 2022)

Cited by in corpus (16)

• TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting
• Spatio-Temporal Wind Speed Forecasting using Graph Networks and Novel Transformer Architectures
• Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art
• TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysis
• OneShotSTL: One-Shot Seasonal-Trend Decomposition For Online Time Series Anomaly Detection And Forecasting
• Deep Learning Based Simulators for the Phosphorus Removal Process Control in Wastewater Treatment via Deep Reinforcement Learning Algorithms
• Machine learning surrogates for efficient hydrologic modeling: Insights from stochastic simulations of managed aquifer recharge
• Monotonic Neural Ordinary Differential Equation: Time-series Forecasting for Cumulative Data
• A Co-training Approach for Noisy Time Series Learning
• Transformers with Attentive Federated Aggregation for Time Series Stock Forecasting
• EnergyPatchTST: Multi-scale Time Series Transformers with Uncertainty Estimation for Energy Forecasting
• Diagnostic Spatio-temporal Transformer with Faithful Encoding
• ADF & TransApp: A Transformer-Based Framework for Appliance Detection Using Smart Meter Consumption Series
• Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representations
• Fourier-Mixed Window Attention: Accelerating Informer for Long Sequence Time-Series Forecasting
• Multi-grained spatial-temporal feature complementarity for accurate online cellular traffic prediction