AIが「なぜ異常と判断したか」を波形で示す反事実波形生成技術を開発 〜インフラ設備や製造装置の異常診断で、原因究明と保守判断を支える説明性の高いAIの実現に向けて〜

2026-05-11 九州大学

本研究における技術（学習段階・運用段階の概要）

＜関連情報＞

• https://www.kyushu-u.ac.jp/ja/notices/view/3105
• https://openreview.net/forum?id=oKUjFiuoVi

時系列分類における潜在構造を用いた反事実的説明 Counterfactual Explanations via Latent Structure for Time Series Classification

Akihiro Yamaguchi, Shizuo Kaji, Kaname Matsue, Ryusei Shingaki
The 29th International Conference on Artificial Intelligence and Statistics (AISTATS 2026)
Open Review.net  Published: 03 Feb 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.