CoMTE: Counterfactual Explanations for Supervised Machine Learning Frameworks on Multivariate Time Series Data
Vitus J. Leung, Emre Ateş, Burak Aksar, Ayse Kivilcim Coskun · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · 2021
CoMTE is a novel explainability technique that provides counterfactual explanations for supervised machine learning frameworks on multivariate time series data. CoMTE outperforms state-of-the-art explainability methods on several different machine learning frameworks and data sets in comprehensibility and robustness. CoMTE can be used to debug machine learning frameworks and gain a better understanding of the underlying multivariate time series data. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525. SAND2021-1686 O