arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2504.05024cs.LG
收藏

基于ECLAD-ts的时间序列概念提取

Concept Extraction for Time Series with ECLAD-ts

Institute for Data Science in Mechanical Engineering (DSME), RWTH Aachen University(亚琛工业大学机械工程数据科学研究所(DSME))

Antonia Holzapfel, Andres Felipe Posada-Moreno, Sebastian Trimpe

AI总结:

针对时间序列分类CNN的黑箱问题,提出适配时间序列领域的事后全局概念提取方法ECLAD-ts,通过聚类激活图逐时间步聚合结果生成概念并计算重要性,实验验证其可有效解释模型预测过程。

摘要:

用于时间序列分类(TSC)的卷积神经网络(CNN)正越来越多地应用于从质量预测到医疗诊断的各类场景。这类模型的黑箱特性使得人们难以理解其预测过程。这一问题至关重要,因为CNN容易学习到捷径和偏差,会削弱其鲁棒性以及与人类预期的一致性。要评估模型是否在使用这类机制及相关风险,必须提供能反映模型内部运作机制的解释。概念提取(CE)方法可提供这类解释,但目前大多是针对图像领域开发的,在时间序列领域仍存在空白。\n在本研究中,我们基于图像领域CE方法的思路,提出了一种适配时间序列领域的概念提取与定位方法。我们提出了全新的ECLAD-ts方法,该方法基于模型在不同抽象层级对输入子集的编码方式,提供事后全局解释。为此,我们通过对CNN激活图进行逐时间步聚合后聚类来生成概念,并根据概念对预测过程的影响计算其重要性。我们在合成数据集和自然数据集上评估了所提方法,还通过实验结果分析了CE在时间序列领域的优势与局限性。结果表明,ECLAD-ts能够利用模型的内部表征有效解释模型,为理解其预测过程提供有用的洞见。

英文摘要:

Convolutional neural networks (CNNs) for time series classification (TSC) are being increasingly used in applications ranging from quality prediction to medical diagnosis. The black box nature of these models makes understanding their prediction process difficult. This issue is crucial because CNNs are prone to learning shortcuts and biases, compromising their robustness and alignment with human expectations. To assess whether such mechanisms are being used and the associated risk, it is essential to provide model explanations that reflect the inner workings of the model. Concept Extraction (CE) methods offer such explanations, but have mostly been developed for the image domain so far, leaving a gap in the time series domain. In this work, we present a CE and localization method tailored to the time series domain, based on the ideas of CE methods for images. We propose the novel method ECLAD-ts, which provides post-hoc global explanations based on how the models encode subsets of the input at different levels of abstraction. For this, concepts are produced by clustering timestep-wise aggregations of CNN activation maps, and their importance is computed based on their impact on the prediction process. We evaluate our method on synthetic and natural datasets. Furthermore, we assess the advantages and limitations of CE in time series through empirical results. Our results show that ECLAD-ts effectively explains models by leveraging their internal representations, providing useful insights about their prediction process.

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。

↑