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 2204.03429cs.AIcs.SC
收藏

通过约束放松发现反事实推理

Finding Counterfactual Explanations through Constraint Relaxations

SFI Centre for Research Training in AI(SFI人工智能研究培训中心);Insight Centre for Data Analytics(Insight数据分析中心);Confirm Centre for Smart Manufacturing(Confirm智能制造中心);University College Cork(科克大学学院)

Sharmi Dev Gupta, Begum Genc, Barry O'Sullivan

摘要:

交互式约束系统往往遭受不可行性(没有解决方案),由于冲突的用户约束。恢复不可行性的一种常见方法是消除导致系统冲突的约束。这种方法允许系统提供如下解释:“如果用户愿意放弃他们的一些约束,则存在解决方案”。然而,人们可以批评这种形式的解释,因为它不是很有信息性。反事实解释是一种解释,它可以通过帮助用户理解哪些更改可以应用于现有约束而不是删除它们来为用户恢复可行性提供基础。这种方法已经在机器学习领域得到了广泛的研究,但需要在约束满足的背景下进行更彻底的调查。我们提出了一种基于过约束约束满足问题中的冲突检测和最大松弛的迭代法,以帮助计算反事实解释。

英文摘要:

Interactive constraint systems often suffer from infeasibility (no solution) due to conflicting user constraints. A common approach to recover infeasibility is to eliminate the constraints that cause the conflicts in the system. This approach allows the system to provide an explanation as: "if the user is willing to drop out some of their constraints, there exists a solution". However, one can criticise this form of explanation as not being very informative. A counterfactual explanation is a type of explanation that can provide a basis for the user to recover feasibility by helping them understand which changes can be applied to their existing constraints rather than removing them. This approach has been extensively studied in the machine learning field, but requires a more thorough investigation in the context of constraint satisfaction. We propose an iterative method based on conflict detection and maximal relaxations in over-constrained constraint satisfaction problems to help compute a counterfactual explanation.

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。

↑