arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.03048cs.AI
收藏

从鲁棒性到可解释性,再回到鲁棒性

From Robustness to Explainability and Back Again

University of Toulouse(图卢兹大学);IRIT(信息学、机器人学与微电子学研究所)

Xuanxiang Huang, Joao Marques-Silva

AI总结:

本文针对形式化可解释性在深度神经网络等分类器上可扩展性不足的问题,提出通过至多线性数量的鲁棒性查询计算形式化解释的高效算法,并推广解释定义以兼容不同距离范数和目标鲁棒程度。

摘要:

形式化可解释性保证了所计算解释的严谨性,因此在严谨性至关重要的领域(包括那些被视为高风险的领域)中极为重要。遗憾的是,自其诞生以来,形式化可解释性一直受到可扩展性不佳的阻碍。目前,这一局限对于若干类分类器仍然存在,其中最显著的是深度神经网络。本文解决形式化可解释性可扩展性差的问题,提出了用于计算形式化解释的新型高效算法。该新算法通过改为回答若干鲁棒性查询来计算解释,并且此类查询的数量相对于特征数量至多为线性。因此,所提出的算法在形式化可解释性的实际复杂度与鲁棒性的实际复杂度之间建立了直接联系。为实现所提出的目标,本文推广了形式化解释的定义,从而允许使用基于不同距离范数的鲁棒性工具,并依据某个目标鲁棒性程度进行推理。初步实验验证了所提方法的实际效率。

英文摘要:

Formal explainability guarantees the rigor of computed explanations, and so it is paramount in domains where rigor is critical, including those deemed high-risk. Unfortunately, since its inception formal explainability has been hampered by poor scalability. At present, this limitation still holds true for some families of classifiers, the most significant being deep neural networks. This paper addresses the poor scalability of formal explainability and proposes novel efficient algorithms for computing formal explanations. The novel algorithm computes explanations by answering instead a number of robustness queries, and such that the number of such queries is at most linear on the number of features. Consequently, the proposed algorithm establishes a direct relationship between the practical complexity of formal explainability and that of robustness. To achieve the proposed goals, the paper generalizes the definition of formal explanations, thereby allowing the use of robustness tools that are based on different distance norms, and also by reasoning in terms of some target degree of robustness. Preliminary experiments validate the practical efficiency of the proposed approach.

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。

↑