What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspective
arXiv:2206.04101 · doi:10.1145/3597199
Abstract
Algorithmic fairness has attracted increasing attention in the machine learning community. Various definitions are proposed in the literature, but the differences and connections among them are not clearly addressed. In this paper, we review and reflect on various fairness notions previously proposed in machine learning literature, and make an attempt to draw connections to arguments in moral and political philosophy, especially theories of justice. We also consider fairness inquiries from a dynamic perspective, and further consider the long-term impact that is induced by current prediction and decision. In light of the differences in the characterized fairness, we present a flowchart that encompasses implicit assumptions and expected outcomes of different types of fairness inquiries on the data generating process, on the predicted outcome, and on the induced impact, respectively. This paper demonstrates the importance of matching the mission (which kind of fairness one would like to enforce) and the means (which spectrum of fairness analysis is of interest, what is the appropriate analyzing scheme) to fulfill the intended purpose.
References in corpus (35)
- The information bottleneck method
- Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment
- Fairness of Exposure in Rankings
- Actionable Recourse in Linear Classification
- On the (im)possibility of fairness
- Roles for Computing in Social Change
- The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasons
- Towards Long-term Fairness in Recommendation
- A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indices
- A Convex Framework for Fair Regression
- Learning Adversarially Fair and Transferable Representations
- Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved
- The Disparate Effects of Strategic Manipulation
- A Short-term Intervention for Long-term Fairness in the Labor Market
- Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
- Foundations of Structural Causal Models with Cycles and Latent Variables
- Fairness in Algorithmic Decision Making: An Excursion Through the Lens of Causality
- Online Learning with an Unknown Fairness Metric
- Causal Reasoning for Algorithmic Fairness
- Graphs for margins of Bayesian networks
- Fairness in Risk Assessment Instruments: Post-Processing to Achieve Counterfactual Equalized Odds
- Calibrated Fairness in Bandits
- Survey on Causal-based Machine Learning Fairness Notions
- Fairness Violations and Mitigation under Covariate Shift
- Transfer of Machine Learning Fairness across Domains
- Achieving Equalized Odds by Resampling Sensitive Attributes
- Achieving Fairness in the Stochastic Multi-armed Bandit Problem
- The four-fifths rule is not disparate impact: a woeful tale of epistemic trespassing in algorithmic fairness
- Fair Algorithms for Infinite and Contextual Bandits
- Allocating Opportunities in a Dynamic Model of Intergenerational Mobility
- Principal Fairness for Human and Algorithmic Decision-Making
- Unintended Selection: Persistent Qualification Rate Disparities and Interventions
- Model Transferability With Responsive Decision Subjects
- Why Fair Labels Can Yield Unfair Predictions: Graphical Conditions for Introduced Unfairness
- Unfairness Despite Awareness: Group-Fair Classification with Strategic Agents