论文标题
通过单调性形状约束的道义学伦理
Deontological Ethics By Monotonicity Shape Constraints
论文作者
论文摘要
我们证明了现代机器学习系统违反常见的道义伦理原则和社会规范，例如“偏爱不幸的人”和“不要惩罚良好属性”是多么容易。我们建议在某些情况下，可以通过添加形状约束来将模型限制以仅对相关输入的响应，将这种道德原则纳入机器学习模型。我们分析了对个人作用的这些道义论的约束与单方面统计平等和平等机会的基于后果主义团体的公平目标之间的关系。该策略可与敏感属性合作，这些属性是布尔或实现的，例如收入和年龄，并且可以帮助产生更负责任和值得信赖的AI。
We demonstrate how easy it is for modern machine-learned systems to violate common deontological ethical principles and social norms such as "favor the less fortunate," and "do not penalize good attributes." We propose that in some cases such ethical principles can be incorporated into a machine-learned model by adding shape constraints that constrain the model to respond only positively to relevant inputs. We analyze the relationship between these deontological constraints that act on individuals and the consequentialist group-based fairness goals of one-sided statistical parity and equal opportunity. This strategy works with sensitive attributes that are Boolean or real-valued such as income and age, and can help produce more responsible and trustworthy AI.
