Gradient-based Model Shortcut Detection for Time Series Classification
This addresses the under-explored issue of internal bias in time series models, which is incremental as it builds on existing shortcut detection work by focusing on point-based behavior.
The paper tackles the problem of deep neural networks relying on spurious correlations or shortcuts in time series classification, proposing a gradient-based detection method that identifies point-based shortcuts without needing test data or clean training classes, and tests it on UCR datasets.
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 point-based shortcut learning behavior in deep learning time series classification. 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.