AISTATS 2022poster46 citations

LIMESegment: Meaningful, Realistic Time Series Explanations

Torty Sivill, Peter Flach

Abstract

LIME (Locally Interpretable Model-Agnostic Explanations) has become a popular way of generating explanations for tabular, image and natural language models, providing insight into why an instance was given a particular classification. In this paper we adapt LIME to time series classification, an under-explored area with existing approaches failing to account for the structure of this kind of data. We frame the non-trivial challenge of adapting LIME to time series classification as the following open questions: “What is a meaningful interpretable representation of a time series?”, “How does one realistically perturb a time series?” and “What is a local neighbourhood around a time series?”. We propose solutions to all three questions and combine them into a novel time series explanation framework called LIMESegment, which outperforms existing adaptations of LIME to time series on a variety of classification tasks.

BibTeX
@InProceedings{pmlr-v151-sivill22a,
  title = 	 { LIMESegment: Meaningful, Realistic Time Series Explanations },
  author =       {Sivill, Torty and Flach, Peter},
  booktitle = 	 {Proceedings of The 25th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {3418--3433},
  year = 	 {2022},
  editor = 	 {Camps-Valls, Gustau and Ruiz, Francisco J. R. and Valera, Isabel},
  volume = 	 {151},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {28--30 Mar},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v151/sivill22a/sivill22a.pdf},
  url = 	 {https://proceedings.mlr.press/v151/sivill22a.html},
  abstract = 	 { LIME (Locally Interpretable Model-Agnostic Explanations) has become a popular way of generating explanations for tabular, image and natural language models, providing insight into why an instance was given a particular classification. In this paper we adapt LIME to time series classification, an under-explored area with existing approaches failing to account for the structure of this kind of data. We frame the non-trivial challenge of adapting LIME to time series classification as the following open questions: “What is a meaningful interpretable representation of a time series?”, “How does one realistically perturb a time series?” and “What is a local neighbourhood around a time series?”. We propose solutions to all three questions and combine them into a novel time series explanation framework called LIMESegment, which outperforms existing adaptations of LIME to time series on a variety of classification tasks. }
}
LIMESegment: Meaningful, Realistic Time Series Explanations · AISTATS 2022