Interactive Counterfactual Generation for Univariate Time Series

TL;DR

This paper introduces an interactive method for generating counterfactual explanations for univariate time series classification, using 2D projections and decision boundary maps to improve interpretability and user understanding.

Contribution

It presents a novel interactive approach that leverages 2D projections and inverse techniques to generate counterfactuals, enhancing interpretability of time series models.

Findings

Improved interpretability demonstrated on ECG5000 dataset

User interactions facilitate understanding of model decisions

Potential for extension to multivariate time series

Abstract

We propose an interactive methodology for generating counterfactual explanations for univariate time series data in classification tasks by leveraging 2D projections and decision boundary maps to tackle interpretability challenges. Our approach aims to enhance the transparency and understanding of deep learning models' decision processes. The application simplifies the time series data analysis by enabling users to interactively manipulate projected data points, providing intuitive insights through inverse projection techniques. By abstracting user interactions with the projected data points rather than the raw time series data, our method facilitates an intuitive generation of counterfactual explanations. This approach allows for a more straightforward exploration of univariate time series data, enabling users to manipulate data points to comprehend potential outcomes of hypothetical scenarios. We validate this method using the ECG5000 benchmark dataset, demonstrating significant improvements in interpretability and user understanding of time series classification. The results indicate a promising direction for enhancing explainable AI, with potential applications in various domains requiring transparent and interpretable deep learning models. Future work will explore the scalability of this method to multivariate time series data and its integration with other interpretability techniques.