Affiliation:
1. Scuola Normale Superiore, Italy and ISTI-CNR, Italy
2. University of Pisa, Italy
3. ISTI-CNR, Italy
4. Scuola Normale Superiore, Italy
Abstract
The growing availability of time series data has increased the usage of classifiers for this data type. Unfortunately, state-of-the-art time series classifiers are black-box models and, therefore, not usable in critical domains such as healthcare or finance, where explainability can be a crucial requirement. This paper presents a framework to explain the predictions of any black-box classifier for univariate and multivariate time series. The provided explanation is composed of three parts. First, a saliency map highlighting the most important parts of the time series for the classification. Second, an instance-based explanation exemplifies the black-box’s decision by providing a set of prototypical and counterfactual time series. Third, a factual and counterfactual rule-based explanation, revealing the reasons for the classification through logical conditions based on subsequences that must, or must not, be contained in the time series. Experiments and benchmarks show that the proposed method provides faithful, meaningful, stable, and interpretable explanations.
Publisher
Association for Computing Machinery (ACM)
Reference98 articles.
1. Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
2. Eirikur Agustsson Sage Alexander Radu Timofte and Luc Van Gool. 2017. Optimal transport maps for distribution preserving operations on latent spaces of Generative Models. (11 2017).
3. Contrastive Explanations to Classification Systems Using Sparse Dictionaries
4. Hiba Arnout, Mennatallah El-Assady, Daniela Oelke, and Daniel A. Keim. 2019. Towards a rigorous evaluation of XAI methods on time series. In 2019 IEEE/CVF International Conference on Computer Vision Workshops, ICCV Workshops 2019, Seoul, Korea (South), October 27–28, 2019. IEEE, 4197–4201. DOI:https://doi.org/10.1109/ICCVW.2019.00516
5. Counterfactual Explanations for Multivariate Time Series