DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervision
This addresses fairness in mission-critical Web applications by improving predictions at both group and individual levels, representing an incremental advance over single-criterion methods.
The paper tackles algorithmic fairness by proposing DualFair, a self-supervised model that jointly optimizes group and counterfactual fairness to debias sensitive attributes like gender and race in learned representations, with extensive analysis confirming its validity and synergy across multiple datasets.
Algorithmic fairness has become an important machine learning problem, especially for mission-critical Web applications. This work presents a self-supervised model, called DualFair, that can debias sensitive attributes like gender and race from learned representations. Unlike existing models that target a single type of fairness, our model jointly optimizes for two fairness criteria - group fairness and counterfactual fairness - and hence makes fairer predictions at both the group and individual levels. Our model uses contrastive loss to generate embeddings that are indistinguishable for each protected group, while forcing the embeddings of counterfactual pairs to be similar. It then uses a self-knowledge distillation method to maintain the quality of representation for the downstream tasks. Extensive analysis over multiple datasets confirms the model's validity and further shows the synergy of jointly addressing two fairness criteria, suggesting the model's potential value in fair intelligent Web applications.