Self-Interpretable Time Series Prediction with Counterfactual Explanations

by   Jingquan Yan, et al.

Interpretable time series prediction is crucial for safety-critical areas such as healthcare and autonomous driving. Most existing methods focus on interpreting predictions by assigning important scores to segments of time series. In this paper, we take a different and more challenging route and aim at developing a self-interpretable model, dubbed Counterfactual Time Series (CounTS), which generates counterfactual and actionable explanations for time series predictions. Specifically, we formalize the problem of time series counterfactual explanations, establish associated evaluation protocols, and propose a variational Bayesian deep learning model equipped with counterfactual inference capability of time series abduction, action, and prediction. Compared with state-of-the-art baselines, our self-interpretable model can generate better counterfactual explanations while maintaining comparable prediction accuracy.


page 1

page 2

page 3

page 4


What went wrong and when? Instance-wise Feature Importance for Time-series Models

Multivariate time series models are poised to be used for decision suppo...

Generating Sparse Counterfactual Explanations For Multivariate Time Series

Since neural networks play an increasingly important role in critical se...

Conditional Generative Models for Counterfactual Explanations

Counterfactual instances offer human-interpretable insight into the loca...

Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency

Interpreting time series models is uniquely challenging because it requi...

Counterfactual Explanations for Land Cover Mapping in a Multi-class Setting

Counterfactual explanations are an emerging tool to enhance interpretabi...

TimeTuner: Diagnosing Time Representations for Time-Series Forecasting with Counterfactual Explanations

Deep learning (DL) approaches are being increasingly used for time-serie...

Please sign up or login with your details

Forgot password? Click here to reset