Conditional Learning of Fair Representations
This addresses fairness in machine learning for classification tasks, but it is incremental as it builds on existing fair representation learning approaches.
The paper tackles the problem of learning fair representations to mitigate disparities in classification across demographic subgroups, achieving a better utility-fairness trade-off on balanced datasets compared to existing methods.
We propose a novel algorithm for learning fair representations that can simultaneously mitigate two notions of disparity among different demographic subgroups in the classification setting. Two key components underpinning the design of our algorithm are balanced error rate and conditional alignment of representations. We show how these two components contribute to ensuring accuracy parity and equalized false-positive and false-negative rates across groups without impacting demographic parity. Furthermore, we also demonstrate both in theory and on two real-world experiments that the proposed algorithm leads to a better utility-fairness trade-off on balanced datasets compared with existing algorithms on learning fair representations for classification.