arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.13623cs.LGcs.AI
收藏

使用函数分解统一基于归因的解释

Unifying Attribution-Based Explanations Using Functional Decomposition

Ghent University(根特大学);VIB Inflammation Research Center(VIB炎症研究中心)

Arne Gevaert, Yvan Saeys

AI总结:

本文提出了一个统一基于归因的解释方法框架,通过引入基于移除的归因方法(RBAMs)和规范加性分解(CAD),揭示了现有方法与博弈论的联系,并为开发新的高效近似方法提供了理论基础。

摘要:

机器学习中的黑盒问题促使人们为复杂模型引入了不断增加的解释方法集合。这些解释具有不同的属性,进而导致了方法选择问题:对于给定的用例,哪种解释方法最合适?在这项工作中,我们提出了一个统一基于归因的解释方法框架,为严格研究解释的相似性和差异性迈出了一步。我们首先引入了基于移除的归因方法(RBAMs),并展示了广泛选择的现有方法都可以被视为此类 RBAMs。然后,我们引入了规范加性分解(CAD)。这是一种基于移除(组)特征的中心思想对任何函数进行加性分解的一般构造。我们进一步证明,确实每一个有效的加性分解都是 CAD 的一个实例,并且任何基于移除的归因方法都与特定的 CAD 相关联。接下来,我们展示了任何基于移除的归因方法都可以完全定义为特定(可能是常数偏移的)合作博弈的博弈论值或交互指数,该博弈是使用该方法相应的 CAD 定义的。然后,我们利用这种内在联系来定义解释方法特定行为的形式化描述(我们称之为功能公理),并识别归因方法相应的 CAD 和博弈论值或交互指数上的充分条件,在这些条件下,保证该归因方法遵循这些功能公理。最后,我们展示了如何使用这个统一框架为现有解释方法开发新的、高效的近似。

英文摘要:

The black box problem in machine learning has led to the introduction of an ever-increasing set of explanation methods for complex models. These explanations have different properties, which in turn has led to the problem of method selection: which explanation method is most suitable for a given use case? In this work, we propose a unifying framework of attribution-based explanation methods, which provides a step towards a rigorous study of the similarities and differences of explanations. We first introduce removal-based attribution methods (RBAMs), and show that an extensively broad selection of existing methods can be viewed as such RBAMs. We then introduce the canonical additive decomposition (CAD). This is a general construction for additively decomposing any function based on the central idea of removing (groups of) features. We proceed to show that indeed every valid additive decomposition is an instance of the CAD, and that any removal-based attribution method is associated with a specific CAD. Next, we show that any removal-based attribution method can be completely defined as a game-theoretic value or interaction index for a specific (possibly constant-shifted) cooperative game, which is defined using the corresponding CAD of the method. We then use this intrinsic connection to define formal descriptions of specific behaviours of explanation methods, which we also call functional axioms, and identify sufficient conditions on the corresponding CAD and game-theoretic value or interaction index of an attribution method under which the attribution method is guaranteed to adhere to these functional axioms. Finally, we show how this unifying framework can be used to develop new, efficient approximations for existing explanation methods.

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。

↑