SLIDE: A surrogate fairness constraint to ensure fairness consistency. (October 2022)

• Record Type: Journal Article
• Authors: Kim, Kunwoong; Ohn, Ilsang; Kim, Sara; Kim, Yongdai
• Is Part Of: Neural networks. Volume 154(2022)
• Page Start: 441
• Page End: 454
• Publication Date: 2022-10
• Subjects: Fairness AI -- Learning theory -- Machine learning -- Supervised learning -- Classification; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2022.07.027
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: As they take a crucial role in social decision makings, AI algorithms based on ML models should be not only accurate but also fair. Among many algorithms for fair AI, learning a prediction ML model by minimizing the empirical risk (e.g., cross-entropy) subject to a given fairness constraint has received much attention. To avoid computational difficulty, however, a given fairness constraint is replaced by a surrogate fairness constraint as the 0–1 loss is replaced by a convex surrogate loss for classification problems. In this paper, we investigate the validity of existing surrogate fairness constraints and propose a new surrogate fairness constraint called SLIDE, which is computationally feasible and asymptotically valid in the sense that the learned model satisfies the fairness constraint asymptotically and achieves a fast convergence rate. Numerical experiments confirm that the SLIDE works well for various benchmark datasets.