Abstract
An ideal time series classification (TSC) should be able to capture invariant representations, but achieving reliable performance on out-of-distribution (OOD) data remains a core obstacle. This obstacle arises from the way models inherently entangle domain-specific and label-relevant features, resulting in spurious correlations. While feature disentanglement aims to solve this, current methods are largely unguided, lacking the semantic direction required to isolate truly universal features. To address this, we propose an end-to-end Energy-Regularized Information for Shift-Robustness (ERIS) framework to enable guided and reliable feature disentanglement. The core idea is that effective disentanglement requires not only mathematical constraints but also semantic guidance to anchor the separation process. ERIS incorporates three key mechanisms to achieve this goal: energy-guided calibration, weight-level orthogonality strategy, and adversarial generalization mechanism.
Methodology
The ERIS framework comprises three key components working in synergy: (1) Energy-Guided Calibration mechanism that leverages domain-specific energy (DSE) and label-specific energy (LSE) functions to provide semantic guidance for feature separation, (2) Weight-Level Orthogonality strategy that enforces structural independence between parameter subspaces, ensuring the domain and label representations remain disentangled, and (3) Adversarial Generalization mechanism that enhances robustness through structured perturbations and domain alignment, promoting invariant feature learning across different distributions.
Main Result
More Results
Citation
@misc{wu2025erisenergyguidedfeaturedisentanglement,
title={ERIS: An Energy-Guided Feature Disentanglement Framework for Out-of-Distribution Time Series Classification},
author={Xin Wu and Fei Teng and Ji Zhang and Xingwang Li and Yuxuan Liang},
year={2025},
eprint={2508.14134},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2508.14134},
}