Counterfactual Explanations via Latent Structure for Time Series Classification

Akihiro Yamaguchi, Shizuo Kaji, Kaname Matsue, Ryusei Shingaki
Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, PMLR 300:2656-2664, 2026.

Abstract

There is a growing need for explainability in time series classification. Counterfactual (CF) generation creates in-distribution synthetic instances that flip the prediction to a desired class. We propose CELT, a model-agnostic CF generation method for time-series classifiers, including non-differentiable and one-class models. In the development phase, CELT learns a structured latent space in which desired-class latent instances form clusters and other latent instances are pushed away. In addition, the design enables segment-wise, time-local edits. In the deployment phase, CELT efficiently generates CFs by editing a minimal number of time-local segments, guided by the learned structure. We formulate both phases as mathematically sound optimization problems that uniformly handle supervised and one-class classification, and we demonstrate effectiveness on UCR datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v300-yamaguchi26a, title = { Counterfactual Explanations via Latent Structure for Time Series Classification }, author = {Yamaguchi, Akihiro and Kaji, Shizuo and Matsue, Kaname and Shingaki, Ryusei}, booktitle = {Proceedings of The 29th International Conference on Artificial Intelligence and Statistics}, pages = {2656--2664}, year = {2026}, editor = {Khan, Emtiyaz and Li, Yingzhen and Solin, Arno and Ramdas, Aaditya}, volume = {300}, series = {Proceedings of Machine Learning Research}, month = {02--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v300/main/assets/yamaguchi26a/yamaguchi26a.pdf}, url = {https://proceedings.mlr.press/v300/yamaguchi26a.html}, abstract = { There is a growing need for explainability in time series classification. Counterfactual (CF) generation creates in-distribution synthetic instances that flip the prediction to a desired class. We propose CELT, a model-agnostic CF generation method for time-series classifiers, including non-differentiable and one-class models. In the development phase, CELT learns a structured latent space in which desired-class latent instances form clusters and other latent instances are pushed away. In addition, the design enables segment-wise, time-local edits. In the deployment phase, CELT efficiently generates CFs by editing a minimal number of time-local segments, guided by the learned structure. We formulate both phases as mathematically sound optimization problems that uniformly handle supervised and one-class classification, and we demonstrate effectiveness on UCR datasets. } }
Endnote
%0 Conference Paper %T Counterfactual Explanations via Latent Structure for Time Series Classification %A Akihiro Yamaguchi %A Shizuo Kaji %A Kaname Matsue %A Ryusei Shingaki %B Proceedings of The 29th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2026 %E Emtiyaz Khan %E Yingzhen Li %E Arno Solin %E Aaditya Ramdas %F pmlr-v300-yamaguchi26a %I PMLR %P 2656--2664 %U https://proceedings.mlr.press/v300/yamaguchi26a.html %V 300 %X There is a growing need for explainability in time series classification. Counterfactual (CF) generation creates in-distribution synthetic instances that flip the prediction to a desired class. We propose CELT, a model-agnostic CF generation method for time-series classifiers, including non-differentiable and one-class models. In the development phase, CELT learns a structured latent space in which desired-class latent instances form clusters and other latent instances are pushed away. In addition, the design enables segment-wise, time-local edits. In the deployment phase, CELT efficiently generates CFs by editing a minimal number of time-local segments, guided by the learned structure. We formulate both phases as mathematically sound optimization problems that uniformly handle supervised and one-class classification, and we demonstrate effectiveness on UCR datasets.
APA
Yamaguchi, A., Kaji, S., Matsue, K. & Shingaki, R.. (2026). Counterfactual Explanations via Latent Structure for Time Series Classification . Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 300:2656-2664 Available from https://proceedings.mlr.press/v300/yamaguchi26a.html.

Related Material