Efficient Fairness-Performance Pareto Front Computation
This provides a benchmark for evaluating fairness-performance trade-offs in representation learning, which is incremental as it builds on known intrinsic trade-offs.
The paper tackles the problem of determining the optimal trade-off between fairness and performance in representation learning by proposing a method to compute the true Pareto front without training complex models, showing it can be efficiently solved and validated on real-world datasets.
There is a well known intrinsic trade-off between the fairness of a representation and the performance of classifiers derived from the representation. Due to the complexity of optimisation algorithms in most modern representation learning approaches, for a given method it may be non-trivial to decide whether the obtained fairness-performance curve of the method is optimal, i.e., whether it is close to the true Pareto front for these quantities for the underlying data distribution. In this paper we propose a new method to compute the optimal Pareto front, which does not require the training of complex representation models. We show that optimal fair representations possess several useful structural properties, and that these properties enable a reduction of the computation of the Pareto Front to a compact discrete problem. We then also show that these compact approximating problems can be efficiently solved via off-the shelf concave-convex programming methods. Since our approach is independent of the specific model of representations, it may be used as the benchmark to which representation learning algorithms may be compared. We experimentally evaluate the approach on a number of real world benchmark datasets.