STaT: Resolving Shape Distortion in Non-Stationary Time Series via Tri-Modal Synergy
For time series forecasting practitioners, STaT addresses the trade-off between average error minimization and capturing essential fluctuations, offering a practical solution for non-stationary environments.
STaT introduces a tri-modal architecture (symbolic, temporal, textual) to reduce shape distortion in non-stationary time series forecasting, achieving up to 8.9% improvement in magnitude metrics and 8.5% reduction in shape distortion across eight benchmarks.
Recent research in time series forecasting frequently investigates the integration of textual and visual modalities with numerical models to better navigate non-stationary environments. Despite delivering solid numerical results, existing multi-modal approaches usually encounter a dilemma: prioritizing the minimization of average errors can result in excessively smooth forecasts that overlook essential fluctuations. To resolve this limitation, we introduce STaT, an innovative multimodal architecture for Symbolic-Temporal-Textual Alignment, which seamlessly unites three synergistic modalities. Specifically, the symbolic modality converts continuous time series into discrete tokens, facilitating the accurate identification of structural patterns and turning points; the temporal modality extracts inherent sequential dependencies; and the textual modality leverages domain semantics to steer the macroscopic forecasting trends. Comprehensive evaluations on eight real-world benchmarks indicate that STaT delivers exceptional performance, enhancing conventional magnitude indicators by up to 8.9% while simultaneously decreasing shape distortion by up to 8.5%.