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 2602.09278cs.LG
收藏

白化对解释性能的影响

The effect of whitening on explanation performance

Physikalisch-Technische Bundesanstalt(物理技术联邦机构);Technische Universität Berlin(技术大学柏林);Charité – Universitätsmedizin(夏里特大学医学中心)

Benedict Clark, Stoyan Karastoyanov, Rick Wilming, Stefan Haufe

AI总结:

本文研究数据白化对解释性能的影响,发现特定白化技术可提升解释效果,但效果因方法和模型架构而异。

摘要:

可解释人工智能(XAI)旨在为机器学习模型提供透明的洞察,然而许多特征归因方法的可靠性仍然是关键挑战。先前研究(Haufe等,2014;Wilming等,2022,2023)已表明,这些方法常常错误地赋予非信息性变量(如抑制变量)显著的重要性,导致根本性的误解。由于统计抑制是由特征依赖性引起的,本研究调查数据白化,一种用于去相关性的常见预处理技术,是否可以减轻此类错误。使用已建立的XAI-TRIS基准(Clark等,2024b),该基准提供合成的真实数据和解释正确性的定量测量,我们经验性地评估了16种流行的特征归因方法与5种不同的白化变换结合使用的情况。此外,我们分析了一个最小的线性二维分类问题(Wilming等,2023)以理论评估白化是否能从贝叶斯最优模型中去除抑制特征的影响。我们的结果表明,虽然特定的白化技术可以提高解释性能,但改进的程度在XAI方法和模型架构之间差异显著。这些发现突显了数据非线性、预处理质量和归因保真度之间的复杂关系,强调了预处理技术在提高模型可解释性中的重要作用。

英文摘要:

Explainable Artificial Intelligence (XAI) aims to provide transparent insights into machine learning models, yet the reliability of many feature attribution methods remains a critical challenge. Prior research (Haufe et al., 2014; Wilming et al., 2022, 2023) has demonstrated that these methods often erroneously assign significant importance to non-informative variables, such as suppressor variables, leading to fundamental misinterpretations. Since statistical suppression is induced by feature dependencies, this study investigates whether data whitening, a common preprocessing technique for decorrelation, can mitigate such errors. Using the established XAI-TRIS benchmark (Clark et al., 2024b), which offers synthetic ground-truth data and quantitative measures of explanation correctness, we empirically evaluate 16 popular feature attribution methods applied in combination with 5 distinct whitening transforms. Additionally, we analyze a minimal linear two-dimensional classification problem (Wilming et al., 2023) to theoretically assess whether whitening can remove the impact of suppressor features from Bayes-optimal models. Our results indicate that, while specific whitening techniques can improve explanation performance, the degree of improvement varies substantially across XAI methods and model architectures. These findings highlight the complex relationship between data non-linearities, preprocessing quality, and attribution fidelity, underscoring the vital role of pre-processing techniques in enhancing model interpretability.

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。

↑