Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecasting
This work addresses efficiency and robustness issues in spatio-temporal forecasting for domains such as transportation and meteorology, offering a novel test-time approach that is incremental over existing training-based methods.
The paper tackles the problem of spatio-temporal forecasting under real-world challenges like anomalies and distributional shifts by proposing a test-time computing paradigm called ST-TTC, which uses calibration to correct biases during testing, resulting in improved accuracy and efficiency as demonstrated in experiments on real-world datasets.
Spatio-temporal forecasting is crucial in many domains, such as transportation, meteorology, and energy. However, real-world scenarios frequently present challenges such as signal anomalies, noise, and distributional shifts. Existing solutions primarily enhance robustness by modifying network architectures or training procedures. Nevertheless, these approaches are computationally intensive and resource-demanding, especially for large-scale applications. In this paper, we explore a novel test-time computing paradigm, namely learning with calibration, ST-TTC, for spatio-temporal forecasting. Through learning with calibration, we aim to capture periodic structural biases arising from non-stationarity during the testing phase and perform real-time bias correction on predictions to improve accuracy. Specifically, we first introduce a spectral-domain calibrator with phase-amplitude modulation to mitigate periodic shift and then propose a flash updating mechanism with a streaming memory queue for efficient test-time computation. ST-TTC effectively bypasses complex training-stage techniques, offering an efficient and generalizable paradigm. Extensive experiments on real-world datasets demonstrate the effectiveness, universality, flexibility and efficiency of our proposed method.