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 2310.04178cs.LGcs.AI
收藏

归因稳定性指标介绍:一种面向时间序列可解释人工智能归因的度量方法

Introducing the Attribution Stability Indicator: a Measure for Time Series XAI Attributions

University of Konstanz(康斯坦茨大学)

Udo Schlegel, Daniel A. Keim

AI总结:

针对时间序列归因技术鲁棒性与可信度难评估的问题,提出融入原始序列与扰动实例相关性及归因结果的归因稳定性指标ASI,并通过降维归因分析与三个数据集的分数分布验证其属性。

摘要:

鉴于金融、天气预报、医疗等领域的时间序列数据规模日益增长且复杂度普遍提升,业界对能够为底层模式与关联关系提供可解释洞见的高性能模型的需求不断攀升。归因技术可从时间序列模型中提取解释以获取洞见,但其鲁棒性与可信度难以评估。我们提出归因稳定性指标(Attribution Stability Indicator,ASI),这是一种将鲁棒性与可信度纳入时间序列归因技术属性考量的度量方法。我们对扰动分析进行了扩展,加入了原始时间序列与扰动实例的相关性以及归因结果,以将所需属性纳入该度量中。我们通过在降维空间中开展归因分析,以及ASI分数在三个完整时间序列分类数据集上的分布情况,验证了这些所需属性。

英文摘要:

Given the increasing amount and general complexity of time series data in domains such as finance, weather forecasting, and healthcare, there is a growing need for state-of-the-art performance models that can provide interpretable insights into underlying patterns and relationships. Attribution techniques enable the extraction of explanations from time series models to gain insights but are hard to evaluate for their robustness and trustworthiness. We propose the Attribution Stability Indicator (ASI), a measure to incorporate robustness and trustworthiness as properties of attribution techniques for time series into account. We extend a perturbation analysis with correlations of the original time series to the perturbed instance and the attributions to include wanted properties in the measure. We demonstrate the wanted properties based on an analysis of the attributions in a dimension-reduced space and the ASI scores distribution over three whole time series classification datasets.

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。

↑