2 papers
cs.LG2026
POEM: Phase-Aware Feature Rotation for Time Series Forecasting Under Periodicity Drift
Jiawen Zhu, Shuhan Liu, Shengxuan Li +2
Deep learning has advanced time series forecasting, but periodicity drift, in which cycle timing and phase vary over time, remains a challenging problem. Existing methods predomina…
cs.LG2026
Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series Forecasting
Jiawen Zhu, Shuhan Liu, Di Weng +1
Non-stationary time series forecasting is challenged by evolving distribution shifts that static models struggle to capture. While Mixture-of-Experts (MoE) architectures offer a pr…