CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlations
This addresses the problem of efficient and interpretable time series forecasting for practitioners, though it appears incremental as it builds on existing lightweight model paradigms.
The paper tackles time series forecasting by proposing CMoS, a super-lightweight model that models spatial correlations between time series chunks instead of learning shape embeddings, achieving state-of-the-art performance with only 1% of the parameters of a lightweight baseline model.
Recent advances in lightweight time series forecasting models suggest the inherent simplicity of time series forecasting tasks. In this paper, we present CMoS, a super-lightweight time series forecasting model. Instead of learning the embedding of the shapes, CMoS directly models the spatial correlations between different time series chunks. Additionally, we introduce a Correlation Mixing technique that enables the model to capture diverse spatial correlations with minimal parameters, and an optional Periodicity Injection technique to ensure faster convergence. Despite utilizing as low as 1% of the lightweight model DLinear's parameters count, experimental results demonstrate that CMoS outperforms existing state-of-the-art models across multiple datasets. Furthermore, the learned weights of CMoS exhibit great interpretability, providing practitioners with valuable insights into temporal structures within specific application scenarios.