Visual Explanations with Attributions and Counterfactuals on Time Series Classification

TL;DR

This paper introduces a visual analytics workflow that combines local attributions and counterfactuals to enhance interpretability of time series classification models, enabling global and local explanations and facilitating hypothesis testing.

Contribution

It adapts local XAI techniques for time series data, creating a unified workflow that integrates explanations, data transformations, and expert feedback for improved model understanding.

Findings

Enables exploration of data transformations and feature relevance.

Identifies model behavior and decision boundaries.

Explains reasons for misclassifications.

Abstract

With the rising necessity of explainable artificial intelligence (XAI), we see an increase in task-dependent XAI methods on varying abstraction levels. XAI techniques on a global level explain model behavior and on a local level explain sample predictions. We propose a visual analytics workflow to support seamless transitions between global and local explanations, focusing on attributions and counterfactuals on time series classification. In particular, we adapt local XAI techniques (attributions) that are developed for traditional datasets (images, text) to analyze time series classification, a data type that is typically less intelligible to humans. To generate a global overview, we apply local attribution methods to the data, creating explanations for the whole dataset. These explanations are projected onto two dimensions, depicting model behavior trends, strategies, and decision boundaries. To further inspect the model decision-making as well as potential data errors, a what-if analysis facilitates hypothesis generation and verification on both the global and local levels. We constantly collected and incorporated expert user feedback, as well as insights based on their domain knowledge, resulting in a tailored analysis workflow and system that tightly integrates time series transformations into explanations. Lastly, we present three use cases, verifying that our technique enables users to (1)~explore data transformations and feature relevance, (2)~identify model behavior and decision boundaries, as well as, (3)~the reason for misclassifications.