CELS: Counterfactual Explanations for Time Series Data via Learned Saliency Maps
CELS: Counterfactual Explanations for Time Series Data via Learned Saliency Maps
复制标题
DOI：
10.1109/bigdata59044.2023.10386229
复制
发表时间：
2023-12
期刊：
影响因子：
--
通讯作者：
Peiyu Li;O. Bahri;S. F. Boubrahimi;S. M. Hamdi
中科院分区：
文献类型：
--
作者：
Peiyu Li;O. Bahri;S. F. Boubrahimi;S. M. Hamdi
随着对可解释机器学习方法的需求增加，越来越需要人类参与为模型决策提供不同的解释。这对于增强基于人工智能的系统的信任和透明度至关重要，从而导致可解释人工智能(XAI)领域的出现。在本文中，我们设计了一个新的反事实解释模型CELS，该模型学习实例兴趣的显著图，并在学习的显著图指导下生成反事实解释。CELS采用一种基于梯度的方法，由三个相互依赖的模块组成，这些模块结合在一起，生成终端用户容易理解的稀疏反事实解释。就我们所知，这是第一次尝试引导扰动通过学习的显著图产生反事实的解释。为了验证我们的模型，我们使用从UCR储存库获得的五个流行的真实世界时间序列数据集进行了实验。实验结果表明，与其他最先进的基线相比，我们的模型在实现反事实解释的稀疏性、贴近度和可解释性方面具有优势。
As the demand for interpretable machine learning approaches increases, there is an increasing need for human involvement to provide diverse explanations for model decisions. This is crucial for enhancing trust and transparency in AI-based systems, leading to the emergence of the Explainable Artificial Intelligence (XAI) field. In this paper, we design a novel counterfactual explanation model, CELS, which learns a saliency map for the interest of an instance and generates a counterfactual explanation guided by the learned saliency map. CELS adopts a gradient-based approach composed of three interdependent modules that combine to generate sparse counterfactual explanations that are easily understood by end users. To the best of our knowledge, this is the first attempt to guide the perturbation to generate a counterfactual explanation via a learned saliency map. To validate our model, we conducted experiments using five popular real-world time-series datasets obtained from the UCR repository. The experimental results demonstrate the superiority of our model in achieving higher sparsity, proximity, and interpretability of counterfactual explanations when compared to other state-of-the-art baselines.