FNNC: Achieving Fairness through Neural Networks
This addresses fairness in classification for applications where bias mitigation is critical, but it appears incremental as it builds on existing constrained optimization approaches with neural networks.
The paper tackles the problem of ensuring fairness in classification models by proposing FNNC, a neural network framework that incorporates fairness constraints like Disparate Impact and Demographic Parity into the loss function using Lagrangian multipliers, achieving performance comparable to or better than state-of-the-art methods.
In classification models fairness can be ensured by solving a constrained optimization problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and Equalized Odds, which are non-decomposable and non-convex. Researchers define convex surrogates of the constraints and then apply convex optimization frameworks to obtain fair classifiers. Surrogates serve only as an upper bound to the actual constraints, and convexifying fairness constraints might be challenging. We propose a neural network-based framework, \emph{FNNC}, to achieve fairness while maintaining high accuracy in classification. The above fairness constraints are included in the loss using Lagrangian multipliers. We prove bounds on generalization errors for the constrained losses which asymptotically go to zero. The network is optimized using two-step mini-batch stochastic gradient descent. Our experiments show that FNNC performs as good as the state of the art, if not better. The experimental evidence supplements our theoretical guarantees. In summary, we have an automated solution to achieve fairness in classification, which is easily extendable to many fairness constraints.