Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective
This addresses forecasting challenges in domains with chaotic data, offering a novel approach with significant efficiency gains.
The paper tackles long-term time series forecasting by modeling time series as observations from chaotic dynamic systems, resulting in Attraos, which outperforms various methods on mainstream and chaotic datasets with only one-twelfth the parameters of PatchTST.
In long-term time series forecasting (LTSF) tasks, an increasing number of models have acknowledged that discrete time series originate from continuous dynamic systems and have attempted to model their dynamical structures. Recognizing the chaotic nature of real-world data, our model, \textbf{\textit{Attraos}}, incorporates chaos theory into LTSF, perceiving real-world time series as observations from unknown high-dimensional chaotic dynamic systems. Under the concept of attractor invariance, Attraos utilizes non-parametric Phase Space Reconstruction embedding and the proposed multi-scale dynamic memory unit to memorize historical dynamics structure and predicts by a frequency-enhanced local evolution strategy. Detailed theoretical analysis and abundant empirical evidence consistently show that Attraos outperforms various LTSF methods on mainstream LTSF datasets and chaotic datasets with only one-twelfth of the parameters compared to PatchTST.