ProtoFair: Fair Self-Supervised Contrastive Learning via Pseudo-Counterfactual Pairs

ArXi:2605.01971v1 Announce Type: new Self-supervised learning methods data. Existing fairness-aware methods address this by redesigning the self-supervised objective itself, limiting portability across the rapidly evolving landscape of self-supervised learning (SSL) frameworks. We propose ProtoFair, a fairness-aware contrastive loss designed to work alongside existing SSL objectives without modifying them. ProtoFair leverages unsupervised prototype clustering to identify pseudo-counterfactual pairs: samples sharing the same cluster assignment but belonging to different sensitive groups.