SoFaiR: Single Shot Fair Representation Learning
This addresses the computational inefficiency and lack of interpretability in fair representation learning for organizations handling sensitive data, though it is incremental in improving existing methods.
The paper tackles the problem of fair representation learning by proposing SoFaiR, a method that generates multiple fairness-information trade-offs with a single trained model, achieving similar performance to multi-shot methods on three datasets.
To avoid discriminatory uses of their data, organizations can learn to map them into a representation that filters out information related to sensitive attributes. However, all existing methods in fair representation learning generate a fairness-information trade-off. To achieve different points on the fairness-information plane, one must train different models. In this paper, we first demonstrate that fairness-information trade-offs are fully characterized by rate-distortion trade-offs. Then, we use this key result and propose SoFaiR, a single shot fair representation learning method that generates with one trained model many points on the fairness-information plane. Besides its computational saving, our single-shot approach is, to the extent of our knowledge, the first fair representation learning method that explains what information is affected by changes in the fairness / distortion properties of the representation. Empirically, we find on three datasets that SoFaiR achieves similar fairness-information trade-offs as its multi-shot counterparts.