Abduction-Based Explanations for Machine Learning Models
Abduction-Based Explanations for Machine Learning Models
复制标题
DOI：
10.1609/aaai.v33i01.33011511
复制
发表时间：
2018-11
期刊：
影响因子：
--
通讯作者：
Alexey Ignatiev;Nina Narodytska;Joao Marques-Silva
中科院分区：
文献类型：
--
作者：
Alexey Ignatiev;Nina Narodytska;Joao Marques-Silva
机器学习（ML）在多种设置中的应用不断增长，激发了计算小型解释对预测的能力。人们普遍认为，对人类决策者更容易理解的小解释更容易。关于计算解释的大多数早期工作都是基于启发式方法，就这些解决方案与基数或子集中的最近距离解释的距离有多近。本文开发了用于计算任何ML模型的解释的约束 - 无形解决方案。所提出的解决方案利用了绑架推理，并强加了要求使用某些目标约束推理系统将ML模型表示为约束的一组，可以用某些Oracle来回答决策问题。在著名数据集上获得的实验结果验证了所提出的方法的可扩展性以及计算解决方案的质量。
The growing range of applications of Machine Learning (ML) in a multitude of settings motivates the ability of computing small explanations for predictions made. Small explanations are generally accepted as easier for human decision makers to understand. Most earlier work on computing explanations is based on heuristic approaches, providing no guarantees of quality, in terms of how close such solutions are from cardinality- or subset-minimal explanations. This paper develops a constraint-agnostic solution for computing explanations for any ML model. The proposed solution exploits abductive reasoning, and imposes the requirement that the ML model can be represented as sets of constraints using some target constraint reasoning system for which the decision problem can be answered with some oracle. The experimental results, obtained on well-known datasets, validate the scalability of the proposed approach as well as the quality of the computed solutions.