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 2102.10878cs.GTmath.PR
收藏

机器学习模型的博弈论群体特征解释的稳定性理论

Stability theory of game-theoretic group feature explanations for machine learning models

Alexey Miroshnikov, Konstandinos Kotsiopoulos, Khashayar Filom, Arjun Ravi Kannan

AI总结:

本文针对机器学习特征归因,建立边际与条件解释的稳定性理论,并提出基于依赖性的群体解释方法,证明其能稳定边际算子并统一两类解释。

摘要:

本文研究机器学习(ML)模型的特征归因,这些归因源自线性博弈值和联盟值,它们被定义为适当函数空间上的算子。主要关注基于条件期望和边际期望的随机博弈。我们工作的第一部分通过为边际解释和条件解释建立一定的界,为这些解释算子构建了稳定性理论。随后阐明了两种博弈之间的差异,例如表明边际解释在某些自然设计的域上可能变得不连续,而条件解释保持稳定。在我们工作的第二部分,基于具有联盟结构的博弈值设计了群体解释方法,其中特征根据依赖性进行分组。我们通过分析表明,以这种方式对特征进行分组在群体和个体两个层面上都对边际算子具有稳定化作用,并允许统一边际解释和条件解释。我们的结果在若干数值实验中得到验证,其中使用了一种基于信息论的依赖性度量进行分组。

英文摘要:

In this article, we study feature attributions of Machine Learning (ML) models originating from linear game values and coalitional values defined as operators on appropriate functional spaces. The main focus is on random games based on the conditional and marginal expectations. The first part of our work formulates a stability theory for these explanation operators by establishing certain bounds for both marginal and conditional explanations. The differences between the two games are then elucidated, such as showing that the marginal explanations can become discontinuous on some naturally-designed domains, while the conditional explanations remain stable. In the second part of our work, group explanation methodologies are devised based on game values with coalition structure, where the features are grouped based on dependencies. We show analytically that grouping features this way has a stabilizing effect on the marginal operator on both group and individual levels, and allows for the unification of marginal and conditional explanations. Our results are verified in a number of numerical experiments where an information-theoretic measure of dependence is used for grouping.

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。

↑