Counterfactual Explanations for Multivariate Time Series

Abstract

Multivariate time series are used in many science and engineering domains, including health-care, astronomy, and high-performance computing. A recent trend is to use machine learning (ML) to process this complex data and these ML-based frameworks are starting to play a critical role for a variety of applications. However, barriers such as user distrust or difficulty of debugging need to be overcome to enable widespread adoption of such frameworks in production systems. To address this challenge, we propose a novel explainability technique, <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CoMTE</i> , that provides <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">counterfactual </i> <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">explanations </i> <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">for </i> <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">supervised </i> <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">machine </i> <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">learning </i> <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">frameworks </i> <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">on </i> <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">multivariate </i> <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">time </i> <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">series </i> <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">data</i> . Using various machine learning frameworks and data sets, we compare CoMTE with several state-of-the-art explainability methods and show that we outperform existing methods in comprehensibility and robustness. We also show how CoMTE can be used to debug machine learning frameworks and gain a better understanding of the underlying multivariate time series data.