SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness
arXiv:2006.14168
Abstract
In this paper, we cast fair machine learning as invariant machine learning. We first formulate a version of individual fairness that enforces invariance on certain sensitive sets. We then design a transport-based regularizer that enforces this version of individual fairness and develop an algorithm to minimize the regularizer efficiently. Our theoretical results guarantee the proposed approach trains certifiably fair ML models. Finally, in the experimental studies we demonstrate improved fairness metrics in comparison to several recent fair training procedures on three ML tasks that are susceptible to algorithmic bias.
arXiv commentICLR 2021
References in corpus (19)
- Explaining and Harnessing Adversarial Examples
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
- Certifying Some Distributional Robustness with Principled Adversarial Training
- Learning Adversarially Fair and Transferable Representations
- Fairness Through Computationally-Bounded Awareness
- Online Learning with an Unknown Fairness Metric
- Training individually fair ML models with Sensitive Subspace Robustness
- Calibration for the (Computationally-Identifiable) Masses
- Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming
- Fairness Through Awareness
- Probably Approximately Metric-Fair Learning
- What's in a Name? Reducing Bias in Bios without Access to Protected Attributes
- Two Simple Ways to Learn Individual Fairness Metrics from Data
- Multiaccuracy: Black-Box Post-Processing for Fairness in Classification
- An Empirical Study on Learning Fairness Metrics for COMPAS Data with Human Supervision
- Auditing ML Models for Individual Bias and Unfairness
- Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness
- Debiasing representations by removing unwanted variation due to protected attributes
Cited by in corpus (6)
- Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools
- Fairness Evaluation in Text Classification: Machine Learning Practitioner Perspectives of Individual and Group Fairness
- Regulatory Instruments for Fair Personalized Pricing
- SLIDE: a surrogate fairness constraint to ensure fairness consistency
- Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately
- Individually Fair Gradient Boosting