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 1811.10656cs.AI
收藏

机器学习模型的溯因推理

Abduction-Based Explanations for Machine Learning Models

University of Lisbon(里斯本大学);ISDCT SB RAS(俄罗斯科学院西伯利亚分院系统动力与控制论研究所);VMware(威睿)

Alexey Ignatiev, Nina Narodytska, Joao Marques-Silva

摘要:

机器学习(ML)在众多环境中的应用范围不断扩大,激发了为预测计算小解释的能力。人们普遍认为,简短的解释更容易让人类决策者理解。大多数早期的工作计算的解释是基于启发式的方法,提供没有保证的质量,在如何接近这样的解决方案是从基数或子集最小的解释。本文开发了一种约束不可知的解决方案,用于计算任何ML模型的解释。所提出的解决方案利用溯因推理,并施加的要求,ML模型可以表示为使用一些目标约束推理系统,决策问题可以回答一些预言集的约束。在知名数据集上获得的实验结果验证了所提出方法的可扩展性以及计算解决方案的质量。

英文摘要:

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.

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。

↑