Decorrelation using Optimal Transport
This addresses fairness and ethics in machine learning by improving decorrelation for high-dimensional feature spaces, particularly in applications like jet classification in high-energy physics, though it is incremental relative to existing methods.
The paper tackles the problem of decorrelating feature spaces from protected attributes by introducing a novel method using Convex Neural Optimal Transport Solvers (Cnots), achieving decorrelation levels comparable to state-of-the-art in binary classification and significantly outperforming it in multiclass outputs.
Being able to decorrelate a feature space from protected attributes is an area of active research and study in ethics, fairness, and also natural sciences. We introduce a novel decorrelation method using Convex Neural Optimal Transport Solvers (Cnots) that is able to decorrelate a continuous feature space against protected attributes with optimal transport. We demonstrate how well it performs in the context of jet classification in high energy physics, where classifier scores are desired to be decorrelated from the mass of a jet. The decorrelation achieved in binary classification approaches the levels achieved by the state-of-the-art using conditional normalising flows. When moving to multiclass outputs the optimal transport approach performs significantly better than the state-of-the-art, suggesting substantial gains at decorrelating multidimensional feature spaces.