提出基于高阶模式的时序可解释方法，让模型决策更透明。
C-SHAP for time series: An approach to high-level temporal explanations
- 用高阶模式替代点或子序列，捕捉完整时间模式
- 结合SHAP量化概念对预测的影响程度
- 适用于医疗和工业场景，结果易被人理解
在医疗和工业等高风险领域，AI决策的可解释性至关重要。缺乏对模型推理过程的理解，将难以保证其可靠性。实际应用多依赖时序数据，但相比图像数据，时序数据的可解释AI（XAI）研究仍较薄弱。现有方法多聚焦于单点或子序列的解释，无法全面反映关键模式，也难实现人类可读的解释。本文提出一种概念驱动的时序XAI方法（C-SHAP），将概念定义为从时序数据中提取的高阶模式，并利用SHAP方法评估这些概念对预测的影响。该框架在人体活动识别（HAR）和预测性维护两个真实应用场景中验证了有效性。
原文摘要 · Abstract (English)
In high-stakes domains, such as healthcare and industry, the explainability of AI-based decision-making has become crucial. Without insight into model reasoning, the reliability of these models cannot be ensured. Applications often rely on the time series data type which, unlike the image data type, is underexplored with respect to the development of explainable AI (XAI) techniques. Most existing XAI techniques for time series are focused on point- or subsequence-based explanations. This limits their usability since points and subsequences do not capture all relevant patterns and may not result in human-interpretable explainability. In this paper, we close this gap and propose a concept-based XAI approach (C-SHAP), where concepts are defined as high-level patterns extracted from the time series data. C-SHAP leverages the SHAP method to determine the influence of these concepts on predictions. The effectiveness of the developed framework is illustrated for use cases from healthcare and industry, in the form of Human Activity Recognition (HAR) and predictive maintenance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。