PhaseFormer: From Patches to Phases for Efficient and Effective Time Series Forecasting

ICLR 2026 Conference Submission17678 Authors

Keywords: time series forecasting, nonstationary, efficiency

TL;DR: PhaseFormer replaces patch-based inefficiency with a phase-driven approach, achieving efficient and robust time series forecasting.

Abstract:

Periodicity is a fundamental characteristic of time series data and has long played a central role in forecasting. Recent deep learning methods strengthen the exploitation of periodicity by treating patches as basic tokens, thereby improving predictive effectiveness. However, their efficiency remains a bottleneck due to large parameter counts and heavy computational costs. This paper provides, for the first time, a clear explanation of why patch-level processing is inherently inefficient, supported by strong evidence from real-world data. To address these limitations, we introduce a phase perspective for modeling periodicity and present an efficient yet effective solution, PhaseFormer.
PhaseFormer features phase-wise prediction through compact phase embeddings and efficient cross-phase interaction enabled by a lightweight routing mechanism. Extensive experiments demonstrate that PhaseFormer achieves state-of-the-art performance with around 1k parameters, consistently across benchmark datasets. Notably, it excels on large-scale and complex datasets, where models with comparable efficiency often struggle. This work marks a significant step toward truly efficient and effective time series forecasting.
Code is available at this repository: https://anonymous.4open.science/r/ICLR26-PhaseFormer-17678.

Primary Area: learning on time series and dynamical systems

Submission Number: 17678