Deontological Ethics By Monotonicity Shape Constraints
arXiv:2001.11990
Abstract
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.
AISTATS 2020
References in corpus (12)
- Equality of Opportunity in Supervised Learning
- Counterfactual Fairness
- Fairness of Exposure in Rankings
- FA*IR: A Fair Top-k Ranking Algorithm
- The Measure and Mismeasure of Fairness
- Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
- A Convex Framework for Fair Regression
- Satisfying Real-world Goals with Dataset Constraints
- Empirical Risk Minimization under Fairness Constraints
- Deontological Ethics By Monotonicity Shape Constraints
- Avoiding Resentment Via Monotonic Fairness
- Prediction Rule Reshaping