通过伪反事实对提升自监督学习公平性，不改动原有框架。
ProtoFair: Fair Self-Supervised Contrastive Learning via Pseudo-Counterfactual Pairs
- 用无监督聚类生成跨敏感群体的伪反事实样本对。
- 在CelebA和UTKFace上公平性显著提升，准确率保持竞争力。
- 仅需敏感属性标签，兼容SimCLR与SupCon等主流框架。
自监督学习能生成高质量视觉表征，但现有研究发现这些表征常继承训练数据中的种族偏见。现有公平性方法通过重设计自监督目标来解决，但限制了在快速演进的自监督学习（SSL）框架间的可迁移性。本文提出ProtoFair，一种与现有SSL目标兼容的公平性感知对比损失。该方法利用无监督原型聚类识别伪反事实对：属于不同敏感群体但具有相同聚类标签的样本。通过在嵌入空间中拉近这些内容相似、跨群体的样本，ProtoFair促使编码器学习对敏感属性无关的表征。该方法仅需敏感属性标注，无需目标标签，可无缝集成至SimCLR与SupCon。在CelebA和UTKFace上的实验表明，其在保持竞争性准确率的同时实现一致的公平性提升。
原文摘要 · Abstract (English)
Self-supervised learning methods learn high-quality visual representations, yet recent studies show that these representations often capture demographic biases present in the training 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. By pulling these content-matched, cross-group samples together in the embedding space, ProtoFair encourages the encoder to learn representations that are invariant to the sensitive attribute. The method requires only sensitive attribute annotations, no target labels, and integrates seamlessly with both SimCLR and SupCon. Experiments on CelebA and UTKFace demonstrate consistent fairness improvements while maintaining competitive accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。