Learning Fair and Transferable Representations
This work addresses fairness in machine learning for applications requiring non-discriminatory predictions, but it is incremental as it builds on existing multitask learning and fairness constraints.
The paper tackled the problem of learning fair representations that do not discriminate subgroups, using demographic parity as the fairness metric, and showed that the proposed method outperforms state-of-the-art approaches by a significant margin on three real-world datasets.
Developing learning methods which do not discriminate subgroups in the population is a central goal of algorithmic fairness. One way to reach this goal is by modifying the data representation in order to meet certain fairness constraints. In this work we measure fairness according to demographic parity. This requires the probability of the possible model decisions to be independent of the sensitive information. We argue that the goal of imposing demographic parity can be substantially facilitated within a multitask learning setting. We leverage task similarities by encouraging a shared fair representation across the tasks via low rank matrix factorization. We derive learning bounds establishing that the learned representation transfers well to novel tasks both in terms of prediction performance and fairness metrics. We present experiments on three real world datasets, showing that the proposed method outperforms state-of-the-art approaches by a significant margin.