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 2602.05082cs.LGcs.AIstat.ML
收藏

可靠的解释还是随机噪声?XAI的可靠性度量

Reliable Explanations or Random Noise? A Reliability Metric for XAI

University of Oslo(奥斯陆大学);Aalborg University(奥尔堡大学)

Poushali Sengupta, Sabita Maharjan, Frank Eliassen, Shashi Raj Pandey, Yan Zhang

AI总结:

本文提出了解释可靠性指数(ERI),通过四个可靠性公理评估解释稳定性,揭示现有解释方法在现实部署中的可靠性问题,推动更可信的可解释人工智能系统。

摘要:

近年来,解释复杂机器学习模型的决策在能源系统、医疗、金融和自主系统等高风险领域已成为关键。然而,这些解释的可靠性,即在现实、非对抗性变化下是否保持稳定和一致,仍 largely 未被测量。广泛使用的 SHAP 和集成梯度(IG)等方法虽然受到归因公理的启发,但在系统层面的条件下,如小输入扰动、相关表示和小模型更新时,其解释可能会有显著变化。这种变化性削弱了解释的可靠性,因为可靠的解释应在等效输入表示和小的、不影响性能的模型变化下保持一致。我们引入了解释可靠性指数(ERI),一种度量在四个可靠性公理下解释稳定性的一组指标:对小输入扰动的鲁棒性、在特征冗余下的一致性、模型演变中的平滑性,以及对轻微分布偏移的抗性。对于每个公理,我们推导了正式保证,包括 Lipschitz 型界限和时间稳定性结果。我们进一步提出了 ERI-T,一种专门用于顺序模型的时间可靠性度量,并引入了 ERI-Bench,一个设计用于系统性压力测试解释可靠性在合成和真实世界数据集上的基准。实验结果揭示了流行解释方法的广泛可靠性失败,显示在现实部署条件下,解释可能不稳定。通过暴露和量化这些不稳定性,ERI 使解释可靠性评估变得系统化,并支持更可信的可解释人工智能(XAI)系统。

英文摘要:

In recent years, explaining decisions made by complex machine learning models has become essential in high-stakes domains such as energy systems, healthcare, finance, and autonomous systems. However, the reliability of these explanations, namely, whether they remain stable and consistent under realistic, non-adversarial changes, remains largely unmeasured. Widely used methods such as SHAP and Integrated Gradients (IG) are well-motivated by axiomatic notions of attribution, yet their explanations can vary substantially even under system-level conditions, including small input perturbations, correlated representations, and minor model updates. Such variability undermines explanation reliability, as reliable explanations should remain consistent across equivalent input representations and small, performance-preserving model changes. We introduce the Explanation Reliability Index (ERI), a family of metrics that quantifies explanation stability under four reliability axioms: robustness to small input perturbations, consistency under feature redundancy, smoothness across model evolution, and resilience to mild distributional shifts. For each axiom, we derive formal guarantees, including Lipschitz-type bounds and temporal stability results. We further propose ERI-T, a dedicated measure of temporal reliability for sequential models, and introduce ERI-Bench, a benchmark designed to systematically stress-test explanation reliability across synthetic and real-world datasets. Experimental results reveal widespread reliability failures in popular explanation methods, showing that explanations can be unstable under realistic deployment conditions. By exposing and quantifying these instabilities, ERI enables principled assessment of explanation reliability and supports more trustworthy explainable AI (XAI) systems.

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。

↑