ES-Mask: Evolutionary Strip Mask for Explaining Time Series Prediction (Student Abstract)

Machine learning models are increasingly used in time series prediction with promising results. The model explanation of time series prediction falls behind the model development and makes less sense to users in understanding model decisions. This paper proposes ES-Mask, a post-hoc and model-agnostic evolutionary strip mask-based saliency approach for time series applications. ES-Mask designs the mask consisting of strips with the same salient value in consecutive time steps to produce binary and sustained feature importance scores over time for easy understanding and interpretation of time series. ES-Mask uses an evolutionary algorithm to search for the optimal mask by manipulating strips in rounds, thus is agnostic to models by involving no internal model states in the search. The initial experiments on MIMIC-III data set show that ES-Mask outperforms state-of-the-art methods.

Authors

• Yifei Sun School of Computer Science and Technology, Huazhong University of Science and Technology, China
• Cheng Song School of Computer Science and Technology, Huazhong University of Science and Technology, China
• Feng Lu Huazhong University of Science and Technology
• Wei Li
• Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab, School of Computer Science and Technology, HUST
• Albert Y. Zomaya The Australia-China Joint Research Centre for Energy Informatics and Demand Response Technologies, Centre for Distributed and High Performance Computing, School of Computer Science, The University of Sydney, Australia

Keywords

• Evolutionary Algorithm
• Explainable AI
• Machine Learning
• Time Series