Beyond Individual and Group Fairness
This work addresses fairness in AI systems for stakeholders affected by algorithmic bias, offering a dynamic approach beyond static definitions, though it appears incremental in extending existing fairness frameworks.
The authors tackled the problem of fairness in machine learning by introducing a complaint-driven model that adapts to multiple fairness criteria, addressing their potential incompatibilities. They developed efficient algorithms with vanishing regret in stochastic settings and competitive ratio guarantees in adversarial settings, demonstrating effectiveness on artificial datasets.
We present a new data-driven model of fairness that, unlike existing static definitions of individual or group fairness is guided by the unfairness complaints received by the system. Our model supports multiple fairness criteria and takes into account their potential incompatibilities. We consider both a stochastic and an adversarial setting of our model. In the stochastic setting, we show that our framework can be naturally cast as a Markov Decision Process with stochastic losses, for which we give efficient vanishing regret algorithmic solutions. In the adversarial setting, we design efficient algorithms with competitive ratio guarantees. We also report the results of experiments with our algorithms and the stochastic framework on artificial datasets, to demonstrate their effectiveness empirically.