Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting
This addresses the challenge of inconsistent model performance across different samples in time-series forecasting, which is critical for real-world applications, though it is incremental as it builds on existing models.
The paper tackles the problem of time-series forecasting by introducing TimeFuse, a framework that adaptively fuses multiple models at the sample level, achieving near-universal improvement over state-of-the-art individual models in various forecasting tasks.
Time-series forecasting plays a critical role in many real-world applications. Although increasingly powerful models have been developed and achieved superior results on benchmark datasets, through a fine-grained sample-level inspection, we find that (i) no single model consistently outperforms others across different test samples, but instead (ii) each model excels in specific cases. These findings prompt us to explore how to adaptively leverage the distinct strengths of various forecasting models for different samples. We introduce TimeFuse, a framework for collective time-series forecasting with sample-level adaptive fusion of heterogeneous models. TimeFuse utilizes meta-features to characterize input time series and trains a learnable fusor to predict optimal model fusion weights for any given input. The fusor can leverage samples from diverse datasets for joint training, allowing it to adapt to a wide variety of temporal patterns and thus generalize to new inputs, even from unseen datasets. Extensive experiments demonstrate the effectiveness of TimeFuse in various long-/short-term forecasting tasks, achieving near-universal improvement over the state-of-the-art individual models. Code is available at https://github.com/ZhiningLiu1998/TimeFuse.