通过噪声注入提升视觉变压器的分类公平性，不牺牲任务性能。
FairNVT: Fair Classification via Noise Injection in Vision Transformers
- 用轻量适配器分离任务与敏感属性特征，再注入校准噪声
- 在3个数据集上显著降低敏感属性攻击准确率，提升公平性指标
- 适合需要高公平性的图像/跨模态分类场景
本文提出FairNVT，一种针对预训练视觉变换器的轻量级去偏框架，在保持任务性能的同时提升预测公平性。其核心思路是：减少下游分类器所用表示中的敏感属性信息，可促进更公平的预测。该方法通过轻量适配器学习任务相关和敏感属性嵌入，对敏感嵌入施加校准高斯噪声，并与任务表示融合。结合正交性约束与公平性正则化，共同抑制嵌入中敏感属性泄露，推动更公平的下游预测。在涵盖视觉与语言的三个数据集上，FairNVT有效降低敏感属性攻击准确率，改善人口统计均等差异与等几率差等公平性指标，同时维持具有竞争力的任务性能。
原文摘要 · Abstract (English)
This paper presents FairNVT, a lightweight debiasing framework for pretrained transformer-based encoders that improves prediction fairness while preserving task performance. FairNVT is motivated by the intuition that reducing sensitive-attribute information in the representation used by the downstream classifier can facilitate fairer predictions. Our approach learns task-relevant and sensitive embeddings via lightweight adapters, applies calibrated Gaussian noise to the sensitive embedding, and fuses it with the task representation. Together with orthogonality constraints and fairness regularization, these components jointly reduce sensitive-attribute leakage in the learned embeddings and encourage fairer downstream predictions. Across three datasets spanning vision and language, FairNVT reduces sensitive-attribute attacker accuracy, improves fairness metrics such as demographic parity difference and equalized odds, and maintains competitive task performance.
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。