Repository logo
  • Log In
    New user? Click here to register.Have you forgotten your password?
University College Dublin
    Colleges & Schools
    Statistics
    All of DSpace
  • Log In
    New user? Click here to register.Have you forgotten your password?
  1. Home
  2. Institutes and Centres
  3. Insight Centre for Data Analytics
  4. Insight Research Collection
  5. Instance-Based Counterfactual Explanations for Time Series Classification
 
  • Details
Options

Instance-Based Counterfactual Explanations for Time Series Classification

Author(s)
Delaney, Eoin  
Greene, Derek  
Keane, Mark T.  
Uri
http://hdl.handle.net/10197/25903
Date Issued
2020-09-27
Date Available
2024-05-09T14:53:38Z
Abstract
In recent years there has been a cascade of research in attempting to make AI systems more interpretable by providing explanations; so-called Explainable AI (XAI). Most of this research has dealt with the challenges that arise in explaining black-box deep learning systems in classification and regression tasks, with a focus on tabular and image data; for example, there is a rich seam of work on post-hoc counterfactual explanations for a variety of black-box classifiers (e.g., when a user is refused a loan, the counterfactual explanation tells the user about the conditions under which they would get the loan). However, less attention has been paid to the parallel interpretability challenges arising in AI systems dealing with time series data. This paper advances a novel technique, called Native-Guide, for the generation of proximal and plausible counterfactual explanations for instance-based time series classification tasks (e.g., where users are provided with alternative time series to explain how a classification might change). The Native-Guide method retrieves and uses native in-sample counterfactuals that already exist in the training data as “guides” for perturbation in time series counterfactual
generation. This method can be coupled with both Euclidean and Dynamic Time Warping (DTW) distance measures. After illustrating the technique on a case study involving a climate classification task, we reported on a comprehensive series of experiments on both real-world and synthetic data sets from the UCR archive. These experiments provide computational evidence of the quality of the counterfactual explanations generated.
Sponsorship
Science Foundation Ireland
Other Sponsorship
Insight Research Centre
Type of Material
Journal Article
Subjects

Counterfactual explan...

XCBR

Time series

DOI
10.1007/978-3-030-86957-1_3
Web versions
https://arxiv.org/pdf/2009.13211.pdf
Language
English
Status of Item
Peer reviewed
This item is made available under a Creative Commons License
https://creativecommons.org/licenses/by-nc-nd/3.0/ie/
File(s)
Loading...
Thumbnail Image
Name

Instance-Based Counterfactual Explanations for Time Series Classification.pdf

Size

419.35 KB

Format

Adobe PDF

Checksum (MD5)

40c161aef07463a932b4fb7bd7bad404

Owning collection
Insight Research Collection

Item descriptive metadata is released under a CC-0 (public domain) license: https://creativecommons.org/public-domain/cc0/.
All other content is subject to copyright.

For all queries please contact research.repository@ucd.ie.

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science

  • Cookie settings
  • Privacy policy
  • End User Agreement