Introducing the Attribution Stability Indicator: a Measure for Time Series XAI Attributions
This work addresses the need for reliable interpretability in time series models for domains like finance and healthcare, but it is incremental as it builds on existing perturbation analysis methods.
The paper tackles the problem of evaluating the robustness and trustworthiness of attribution techniques for time series models by proposing the Attribution Stability Indicator (ASI), a measure that incorporates these properties through perturbation analysis and correlation methods, and demonstrates its effectiveness on three time series classification datasets.
Given the increasing amount and general complexity of time series data in domains such as finance, weather forecasting, and healthcare, there is a growing need for state-of-the-art performance models that can provide interpretable insights into underlying patterns and relationships. Attribution techniques enable the extraction of explanations from time series models to gain insights but are hard to evaluate for their robustness and trustworthiness. We propose the Attribution Stability Indicator (ASI), a measure to incorporate robustness and trustworthiness as properties of attribution techniques for time series into account. We extend a perturbation analysis with correlations of the original time series to the perturbed instance and the attributions to include wanted properties in the measure. We demonstrate the wanted properties based on an analysis of the attributions in a dimension-reduced space and the ASI scores distribution over three whole time series classification datasets.