ROSE: Register Assisted General Time Series Forecasting with Decomposed Frequency Learning
Wang, Yihang, Qiu, Yuying, Chen, Peng, Zhao, Kai, Shu, Yang, Rao, Zhongwen, Pan, Lujia, Yang, Bin, Guo, Chenjuan
With the increasing collection of time series data from various domains, there arises a strong demand for general time series forecasting models pre-trained on a large number of time-series datasets to support a variety of downstream prediction tasks. Enabling general time series forecasting faces two challenges: how to obtain unified representations from multi-domian time series data, and how to capture domain-specific features from time series data across various domains for adaptive transfer in downstream tasks. To address these challenges, we propose a Register Assisted General Time Series Forecasting Model with Decomposed Frequency Learning (ROSE), a novel pre-trained model for time series forecasting. ROSE employs Decomposed Frequency Learning for the pre-training task, which decomposes coupled semantic and periodic information in time series with frequency-based masking and reconstruction to obtain unified representations across domains. We also equip ROSE with a Time Series Register, which learns to generate a register codebook to capture domain-specific representations during pre-training and enhances domain-adaptive transfer by selecting related register tokens on downstream tasks. After pre-training on large-scale time series data, ROSE achieves state-of-the-art forecasting performance on 8 real-world benchmarks. Remarkably, even in few-shot scenarios, it demonstrates competitive or superior performance compared to existing methods trained with full data.
May-24-2024
- Country:
- Asia > China (0.14)
- North America > United States
- California (0.14)
- Genre:
- Research Report (1.00)
- Industry:
- Energy > Power Industry (0.46)
- Technology: