让医学图像分类模型在低精度下更公平，避免对特定人群预测偏差。
FairQuant: Fairness-Aware Mixed-Precision Quantization for Medical Image Classification
- 按群体重要性分配不同精度，动态优化每层权重的位数
- 4-6比特平均精度接近8比特全精度，且最差群体表现显著提升
- 适合医疗诊断中需兼顾性能与公平性的轻量化模型部署
通过量化模型参数压缩神经网络，在性能与效率间取得平衡。现有方法如量化感知训练和后训练量化虽能保持压缩后模型的下游性能，但未显式考虑算法公平性影响。本文研究在明确比特预算下，面向医学图像分类的公平性感知混合精度量化方案。提出FairQuant框架，结合群体感知重要性分析、受预算约束的混合精度分配，以及可学习的位感知量化（BAQ）模式，联合优化权重与每单元比特分配，同时引入比特率与公平性正则化。在Fitzpatrick17k与ISIC2019数据集上，基于ResNet18/50、DeiT-Tiny和TinyViT的实验表明：平均4-6比特的FairQuant配置，在恢复接近8比特均匀量化的准确率的同时，显著优于4比特和8比特基准模型的最差群体表现，且在相同预算下具备相当的公平性指标。
原文摘要 · Abstract (English)
Compressing neural networks by quantizing model parameters offers useful trade-off between performance and efficiency. Methods like quantization-aware training and post-training quantization strive to maintain the downstream performance of compressed models compared to the full precision models. However, these techniques do not explicitly consider the impact on algorithmic fairness. In this work, we study fairness-aware mixed-precision quantization schemes for medical image classification under explicit bit budgets. We introduce FairQuant, a framework that combines group-aware importance analysis, budgeted mixed-precision allocation, and a learnable Bit-Aware Quantization (BAQ) mode that jointly optimizes weights and per-unit bit allocations under bitrate and fairness regularization. We evaluate the method on Fitzpatrick17k and ISIC2019 across ResNet18/50, DeiT-Tiny, and TinyViT. Results show that FairQuant configurations with average precision near 4-6 bits recover much of the Uniform 8-bit accuracy while improving worst-group performance relative to Uniform 4- and 8-bit baselines, with comparable fairness metrics under shared budgets.
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。