From Utilitarian to Rawlsian Designs for Algorithmic Fairness
This work addresses the problem of defining and optimizing fairness in algorithmic systems for researchers and practitioners, offering a flexible approach but is incremental in bridging existing ethical theories.
The paper tackles the lack of consensus in measuring algorithmic fairness by proposing a parameterized class of objective functions that interpolates between utilitarian and Rawlsian ethical frameworks, showing that optimal solutions converge to both notions and demonstrating empirically that increasing model complexity can improve both measures on real-world datasets.
There is a lack of consensus within the literature as to how `fairness' of algorithmic systems can be measured, and different metrics can often be at odds. In this paper, we approach this task by drawing on the ethical frameworks of utilitarianism and John Rawls. Informally, these two theories of distributive justice measure the `good' as either a population's sum of utility, or worst-off outcomes, respectively. We present a parameterized class of objective functions that interpolates between these two (possibly) conflicting notions of the `good'. This class is shown to represent a relaxation of the Rawlsian `veil of ignorance', and its sequence of optimal solutions converges to both a utilitarian and Rawlsian optimum. Several other properties of this class are studied, including: 1) a relationship to regularized optimization, 2) feasibility of consistent estimation, and 3) algorithmic cost. In several real-world datasets, we compute optimal solutions and construct the tradeoff between utilitarian and Rawlsian notions of the `good'. Empirically, we demonstrate that increasing model complexity can manifest strict improvements to both measures of the `good'. This work suggests that the proper degree of `fairness' can be informed by a designer's preferences over the space of induced utilitarian and Rawlsian `good'.