We present a method to explain the decisions of black box models for time series classification. The explanation consists of factual and counterfactual shapelet-based rules revealing the reasons for the classification, and of a set of exemplars and counter-exemplars highlighting similarities and differences with the time series under analysis. The proposed method first generates exemplar and counter-exemplar time series in the latent feature space and learns a local latent decision tree classifier. Then, it selects and decodes those respecting the decision rules explaining the decision. Finally, it learns on them a shapelet-tree that reveals the parts of the time series that must, and must not, be contained for getting the returned outcome from the black box. A wide experimentation shows that the proposed method provides faithful, meaningful and interpretable explanations.

Explaining any time series classifier

Spinnato, Francesco;Pedreschi, Dino;Giannotti, Fosca
2020

Abstract

We present a method to explain the decisions of black box models for time series classification. The explanation consists of factual and counterfactual shapelet-based rules revealing the reasons for the classification, and of a set of exemplars and counter-exemplars highlighting similarities and differences with the time series under analysis. The proposed method first generates exemplar and counter-exemplar time series in the latent feature space and learns a local latent decision tree classifier. Then, it selects and decodes those respecting the decision rules explaining the decision. Finally, it learns on them a shapelet-tree that reveals the parts of the time series that must, and must not, be contained for getting the returned outcome from the black box. A wide experimentation shows that the proposed method provides faithful, meaningful and interpretable explanations.
2020
Settore INF/01 - Informatica
2nd IEEE International Conference on Cognitive Machine Intelligence, CogMI 2020
USA
2020
Proceedings - 2020 IEEE 2nd International Conference on Cognitive Machine Intelligence, CogMI 2020
Institute of Electrical and Electronics Engineers Inc.
978-1-7281-4144-2
Exemplars and Counter-Exemplars; Explainable AI; Shapelet-based Rules; Time Series Classification
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11384/137187
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 26
  • ???jsp.display-item.citation.isi??? 14
social impact