Domain Adaptation meets Individual Fairness. And they get along
This work addresses fairness and robustness issues in machine learning models for underrepresented groups, offering a novel connection between fairness and domain adaptation.
The paper tackles the problem of algorithmic bias caused by distributional shifts by showing that individual fairness interventions can improve out-of-distribution accuracy under covariate shift, and that domain adaptation methods like representation alignment can be adapted to enforce individual fairness.
Many instances of algorithmic bias are caused by distributional shifts. For example, machine learning (ML) models often perform worse on demographic groups that are underrepresented in the training data. In this paper, we leverage this connection between algorithmic fairness and distribution shifts to show that algorithmic fairness interventions can help ML models overcome distribution shifts, and that domain adaptation methods (for overcoming distribution shifts) can mitigate algorithmic biases. In particular, we show that (i) enforcing suitable notions of individual fairness (IF) can improve the out-of-distribution accuracy of ML models under the covariate shift assumption and that (ii) it is possible to adapt representation alignment methods for domain adaptation to enforce individual fairness. The former is unexpected because IF interventions were not developed with distribution shifts in mind. The latter is also unexpected because representation alignment is not a common approach in the individual fairness literature.