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 as an upper bound to the actual constraints, and convexifying fairness constraints is 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.

No abstract

We consider the problem of achieving fair classification in Federated Learning (FL) under data heterogeneity. Most of the approaches proposed for fair classification require diverse data that represent the different demographic groups involved. In contrast, it is common for each client to own data that represents only a single demographic group. Hence the existing approaches cannot be adopted for fair classification models at the client level. To resolve this challenge, we propose several aggregation techniques. We empirically validate these techniques by comparing the resulting fairness metrics and accuracy on CelebA, UTK, and FairFace datasets.

No abstract

We formalize a framework for coordinating the funding of projects and sharing the costs among agents with quasi-linear utility functions and individual budgets. Our model contains the classical discrete participatory budgeting model as a special case, while capturing other well-motivated problems. We propose several important axioms and objectives and study how well they can be simultaneously satisfied.One of our main results is that whereas welfare maximization admits an FPTAS, welfare maximization subject to a well-motivated and very weak participation requirement leads to a strong inapproximability result. We show that this result is bypassed if we consider some natural restricted valuations or when we take an average-case heuristic approach.