Preprint: Visual Explanations with Attributions and Counterfactuals on Time Series Classification
- 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 andWith 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.…
Document Type: | Article (unreviewed) |
---|---|
Zitierlink: | https://opus.hs-offenburg.de/8435 | Bibliografische Angaben |
Title (English): | Preprint: Visual Explanations with Attributions and Counterfactuals on Time Series Classification |
Author: | Udo Schlegel, Daniela OelkeStaff MemberGND, Daniel A. Keim, Mennatallah El-Assady |
Year of Publication: | 2023 |
Date of first Publication: | 2023/07/14 |
First Page: | 1 |
Last Page: | 14 |
DOI: | https://doi.org/10.48550/arXiv.2307.08494 |
Language: | English | Inhaltliche Informationen |
Institutes: | Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) |
Collections of the Offenburg University: | Bibliografie |
Tag: | Deep Learning; Explainable AI; Time Series Classification; Visual Analytics | Formale Angaben |
Relevance for "Jahresbericht über Forschungsleistungen": | Keine Relevanz |
Open Access: | Open Access |
Diamond | |
Licence (German): | Creative Commons - CC BY - Namensnennung 4.0 International |
ArXiv Id: | http://arxiv.org/abs/2307.08494 |