Gradient-based Model Shortcut Detection for Time Series Classification

Authors

• Salomon Ibarra, The University of Texas Rio Grande Valley
• Frida Cantu, The University of Texas Rio Grande Valley
• Kaixiong Zhou
• Li Zhang, The University of Texas Rio Grande Valley

Document Type

Conference Proceeding

Publication Date

2026

Abstract

Deep learning models have attracted lots of research attention in time series classification (TSC) task in the past two decades. Recently, deep neural networks (DNN) have surpassed classical distance-based methods and achieved state-of-the-art performance. Despite their promising performance, deep neural networks (DNNs) have been shown to rely on spurious correlations present in the training data, which can hinder generalization. For instance, a model might incorrectly associate the presence of grass with the label "cat" if the training set have majority of cats lying in grassy backgrounds. However, the shortcut behavior of DNNs in time series remain under-explored. Most existing shortcut work are relying on external attributes such as gender, patients group, instead of focus on the internal bias behavior in time series models.In this paper, we take the first step to investigate and establish the point-based shortcut learning behavior in deep learning in time series classification task exists. We further propose a simple detection method based on other class to detect shortcut occurs without relying on test data or clean training classes. We test our proposed method in UCR time series datasets.

Recommended Citation

Ibarra, Salomon, Frida Cantu, Kaixiong Zhou, and Li Zhang. "Gradient-based Model Shortcut Detection for Time Series Classification." In 2025 International Conference on Machine Learning and Applications (ICMLA), pp. 726-731. IEEE, 2025. https://doi.org/10.1109/ICMLA66185.2025.00104

Publication Title

2025 International Conference on Machine Learning and Applications (ICMLA)

DOI

10.1109/ICMLA66185.2025.00104