cs.CVSep 30, 2025

Entropy Guided Dynamic Patch Segmentation for Time Series Transformers

Authors: Sachith Abeywickrama, Emadeldeen Eldele, Min Wu, Xiaoli Li, Chau Yuen

Organizations: School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore · Institute for Infocomm Research, A*STAR, Singapore · Department of Computer Science, Khalifa University, UAE · Information Systems Technology and Design, Singapore University of Technology and Design, Singapore

Abstract

Patch-based transformers have emerged as efficient and improved long-horizon modeling architectures for time series modeling. Yet, existing approaches rely on temporally-agnostic patch construction, where arbitrary starting positions and fixed lengths fracture temporal coherence by splitting natural transitions across boundaries. This naive segmentation often disrupts short-term dependencies and weakens representation learning. We propose a novel Entropy-Guided Dynamic Patch Encoder (EntroPE), as a temporally informed framework that dynamically detects transition points via conditional entropy and dynamically places patch boundaries. This preserves temporal structure while retaining the computational benefits of patching. EntroPE consists of two key modules, namely an Entropy-based Dynamic Patcher (EDP) that applies information-theoretic criteria to locate natural temporal shifts and determine patch boundaries, and an Adaptive Patch Encoder (APE) that employs pooling and cross-attention to capture intra-patch dependencies and produce fixed-size latent representations. Extensive experiments on long-term forecasting, classification, and anomaly detection demonstrate that the proposed method improves both accuracy and efficiency, establishing entropy-guided dynamic patching as a promising new paradigm for time series modeling. Code is available at https://github.com/Sachithx/EntroPE.

Figures & tables

Appendix figures & tables19 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. TimeSqueeze: Dynamic Patching for Efficient Time Series Forecasting

    Mar 11, 2026Sravan Kumar Ankireddy, Nikita Seleznev, Nam H. Nguyen +4Time Series ForecastingTime Series Transformers

  2. Dynamic Tokenization via Reinforcement Patching: End-to-end Training and Zero-shot Transfer

    Mar 27, 2026Yulun Wu, Sravan Kumar Ankireddy, Samuel Sharpe +4Multiscale Time-Series ModelingTime Series Forecasting

  3. IPatch: A Multi-Resolution Transformer Architecture for Robust Time-Series Forecasting

    Mar 25, 2026Aymane Harkati, Moncef Garouani, Olivier Teste +2Robust Time Series ForecastingTime Series Forecasting