arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.01928cs.LGcs.AI
收藏

机器学习中的鲁棒反事实解释:综述

Robust Counterfactual Explanations in Machine Learning: A Survey

Imperial College London(帝国理工学院)

Junqi Jiang, Francesco Leofante, Antonio Rago, Francesca Toni

AI总结:

本综述系统回顾了机器学习中鲁棒反事实解释的研究,分析了鲁棒性形式、现有解决方案及其局限,为未来发展奠定基础。

摘要:

反事实解释(CEs)被倡导为最适合为受机器学习模型预测影响的个体提供算法补救措施。虽然CEs对受影响个体可能有益,但近期工作揭示了在获取CEs的最先进方法中与鲁棒性相关的严重问题。由于鲁棒性的缺乏可能损害CEs的有效性,因此需要采取技术来缓解这一风险。在本综述中,我们回顾了快速增长的鲁棒CEs领域中的工作,并对它们所考虑的鲁棒性形式进行了深入分析。我们还讨论了现有解决方案及其局限性,为未来的发展提供了坚实的基础。

英文摘要:

Counterfactual explanations (CEs) are advocated as being ideally suited to providing algorithmic recourse for subjects affected by the predictions of machine learning models. While CEs can be beneficial to affected individuals, recent work has exposed severe issues related to the robustness of state-of-the-art methods for obtaining CEs. Since a lack of robustness may compromise the validity of CEs, techniques to mitigate this risk are in order. In this survey, we review works in the rapidly growing area of robust CEs and perform an in-depth analysis of the forms of robustness they consider. We also discuss existing solutions and their limitations, providing a solid foundation for future developments.

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。

↑