arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.07082cs.LGcs.AI
收藏

关于时间序列的XAI方法的严格评价

Towards a Rigorous Evaluation of XAI Methods on Time Series

University of Konstanz(康斯坦茨大学);Siemens CT(西门子中央研究院);TU Munich(慕尼黑工业大学)

Udo Schlegel, Hiba Arnout, Mennatallah El-Assady, Daniela Oelke, Daniel A. Keim

摘要:

可解释的人工智能(XAI)方法通常用于解释和调试黑盒机器学习模型。然而,大多数提出的XAI方法本身就是黑盒,并且是为图像设计的。因此,他们依靠视觉可解释性来评估和证明解释。在这项工作中,我们将以前在图像和文本域中使用的XAI方法应用于时间序列。我们提出了一种方法来测试和评估各种XAI方法的时间序列,通过引入新的验证技术,将时间维度。我们进一步进行了初步实验,以评估所选XAI方法解释的质量,并在一系列数据集上使用各种验证方法并检查其质量指标。我们证明,在我们的初步实验中,SHAP对所有模型都是鲁棒的,但其他模型,如DeepLIFT,LRP和显着性图,在特定的架构下工作得更好。

英文摘要:

Explainable Artificial Intelligence (XAI) methods are typically deployed to explain and debug black-box machine learning models. However, most proposed XAI methods are black-boxes themselves and designed for images. Thus, they rely on visual interpretability to evaluate and prove explanations. In this work, we apply XAI methods previously used in the image and text-domain on time series. We present a methodology to test and evaluate various XAI methods on time series by introducing new verification techniques to incorporate the temporal dimension. We further conduct preliminary experiments to assess the quality of selected XAI method explanations with various verification methods on a range of datasets and inspecting quality metrics on it. We demonstrate that in our initial experiments, SHAP works robust for all models, but others like DeepLIFT, LRP, and Saliency Maps work better with specific architectures.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑