fairret: a Framework for Differentiable Fairness Regularization Terms

arXiv:2310.17256v2 Announce Type: replace
Abstract: Current fairness toolkits in machine learning only admit a limited range of fairness definitions and have seen little integration with automatic differentiation libraries, despite the central role these libraries play in modern machine learning pipelines.
We introduce a framework of fairness regularization terms (fairrets) which quantify bias as modular, flexible objectives that are easily integrated in automatic differentiation pipelines. By employing a general definition of fairness in terms of linear-fractional statistics, a wide class of …

abstract arxiv bias cs.lg current definitions differentiable differentiation fairness framework integration libraries machine machine learning modern pipelines regularization role terms type