Counterfactual Explanations for Machine Learning on Multivariate Time Series Data

TL;DR

This paper introduces a novel counterfactual explanation method for supervised machine learning models on multivariate time series data, enhancing trust and interpretability in high-performance computing applications.

Contribution

It presents a new explainability technique that outperforms existing methods in faithfulness and robustness, aiding debugging and understanding of ML models on time series data.

Findings

Outperforms state-of-the-art explainability methods

Improves model debugging and understanding

Enhances trust in ML frameworks for HPC

Abstract

Applying machine learning (ML) on multivariate time series data has growing popularity in many application domains, including in computer system management. For example, recent high performance computing (HPC) research proposes a variety of ML frameworks that use system telemetry data in the form of multivariate time series so as to detect performance variations, perform intelligent scheduling or node allocation, and improve system security. Common barriers for adoption for these ML frameworks include the lack of user trust and the difficulty of debugging. These barriers need to be overcome to enable the widespread adoption of ML frameworks in production systems. To address this challenge, this paper proposes a novel explainability technique for providing counterfactual explanations for supervised ML frameworks that use multivariate time series data. The proposed method outperforms state-of-the-art explainability methods on several different ML frameworks and data sets in metrics such as faithfulness and robustness. The paper also demonstrates how the proposed method can be used to debug ML frameworks and gain a better understanding of HPC system telemetry data.