多线性模型中的原则性多元反事实
Principled Diverse Counterfactuals in Multilinear Models
摘要：
机器学习（ML）应用程序已经自动化了许多现实生活中的任务，改善了私人和公共生活。然而，许多最先进的模型的黑箱性质对模型验证提出了挑战;如何确保算法的决策基于正确的标准，或者它不会歧视某些少数群体？在本文中，我们提出了一种方法来产生不同的反事实的解释，从多线性模型，一个广泛的类，其中包括随机森林，以及贝叶斯网络。
英文摘要：
Machine learning (ML) applications have automated numerous real-life tasks, improving both private and public life. However, the black-box nature of many state-of-the-art models poses the challenge of model verification; how can one be sure that the algorithm bases its decisions on the proper criteria, or that it does not discriminate against certain minority groups? In this paper we propose a way to generate diverse counterfactual explanations from multilinear models, a broad class which includes Random Forests, as well as Bayesian Networks.
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。
