arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.02155cs.LG
收藏

局部置换的拓扑表示

Topological Representations of Local Explanations

New York University(纽约大学);Microsoft Research(微软研究院);University of São Paulo(圣保罗大学);Capital One(第一资本)

Peter Xenopoulos, Gromit Chan, Harish Doraiswamy, Luis Gustavo Nonato, Brian Barr, Claudio Silva

摘要:

局部可解释性方法--那些试图为每个预测产生解释的方法--正变得越来越普遍,因为从业者需要合理化他们的模型输出。然而,比较局部可解释性方法是困难的,因为它们各自产生不同尺度和维度的输出。此外,由于一些可解释性方法的随机性,一种方法的不同运行可能会对给定的观察结果产生矛盾的解释。在本文中,我们提出了一个基于拓扑的框架,从一组本地的解释提取一个简化的表示。我们首先将解释空间和模型预测之间的关系建模为标量函数。然后,我们计算这个函数的拓扑骨架。这种拓扑骨架作为这样的功能,我们使用比较不同的解释方法的签名。我们证明了我们的框架不仅可以可靠地识别可解释性技术之间的差异,而且还提供了稳定的表示。然后,我们将展示如何使用我们的框架来确定适当的参数,局部可解释性方法。我们的框架是简单的,不需要复杂的优化,并可以广泛应用于大多数本地解释方法。我们相信,我们的方法的实用性和多功能性将有助于促进基于拓扑的方法作为一种工具,理解和比较解释方法。

英文摘要:

Local explainability methods -- those which seek to generate an explanation for each prediction -- are becoming increasingly prevalent due to the need for practitioners to rationalize their model outputs. However, comparing local explainability methods is difficult since they each generate outputs in various scales and dimensions. Furthermore, due to the stochastic nature of some explainability methods, it is possible for different runs of a method to produce contradictory explanations for a given observation. In this paper, we propose a topology-based framework to extract a simplified representation from a set of local explanations. We do so by first modeling the relationship between the explanation space and the model predictions as a scalar function. Then, we compute the topological skeleton of this function. This topological skeleton acts as a signature for such functions, which we use to compare different explanation methods. We demonstrate that our framework can not only reliably identify differences between explainability techniques but also provides stable representations. Then, we show how our framework can be used to identify appropriate parameters for local explainability methods. Our framework is simple, does not require complex optimizations, and can be broadly applied to most local explanation methods. We believe the practicality and versatility of our approach will help promote topology-based approaches as a tool for understanding and comparing 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。

↑