L-Drive: Beyond a Single Mapping-Latent Context Drives Time Series Forecasting
For time-series forecasting practitioners, L-Drive addresses the problem of error accumulation during regime changes, offering a more reliable alternative to direct-mapping methods.
L-Drive introduces a latent-context framework for multivariate time-series forecasting that explicitly models high-level dynamics to improve adaptation to distribution shifts and regime changes, achieving better accuracy-efficiency trade-offs.
Mainstream methods for multivariate time-series forecasting largely follow the Direct-Mapping paradigm. They learn a unified mapping from history to the future in the observation space to fit value-level dependencies. However, real-world systems often undergo distribution shifts and regime changes. In such cases, a unified mapping can exhibit response lag around turning points, causing error accumulation within the switching window and reducing forecasting reliability. To address this issue, we propose L-Drive, a change-aware forecasting framework. L-Drive introduces a Latent-Context, to explicitly characterize high-level dynamics evolving over time, and uses gating to modulate increment representations. This provides more timely change cues and improves adaptation to changing segments. In addition, it incorporates patch-shared relative positional basis functions to strengthen intra-segment structural modeling and reduce overfitting caused by absolute-position memorization. Extensive experiments validate the effectiveness of L-Drive and show a better overall trade-off between forecasting accuracy and computational efficiency.