A Reduction to Binary Approach for Debiasing Multiclass Datasets
This addresses fairness in machine learning for domains like social science and healthcare, but it is incremental as it builds on existing debiasing methods.
The paper tackles the problem of enforcing demographic parity in multiclass classification with non-binary sensitive attributes by proposing a reduction-to-binary approach, which improves over baselines in some settings and shows competitive results from independent label debiasing.
We propose a novel reduction-to-binary (R2B) approach that enforces demographic parity for multiclass classification with non-binary sensitive attributes via a reduction to a sequence of binary debiasing tasks. We prove that R2B satisfies optimality and bias guarantees and demonstrate empirically that it can lead to an improvement over two baselines: (1) treating multiclass problems as multi-label by debiasing labels independently and (2) transforming the features instead of the labels. Surprisingly, we also demonstrate that independent label debiasing yields competitive results in most (but not all) settings. We validate these conclusions on synthetic and real-world datasets from social science, computer vision, and healthcare.