Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

FairQuant: Fairness-Aware Mixed-Precision Quantization for Medical Image Classification

Thomas Woergaard, Raghavendra Selvan

TL;DR

FairQuant is introduced, 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.

Abstract

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.

FairQuant: Fairness-Aware Mixed-Precision Quantization for Medical Image Classification

TL;DR

FairQuant is introduced, 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.

Abstract

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.
Paper Structure (5 sections, 3 equations, 2 figures, 1 table)

This paper contains 5 sections, 3 equations, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Method
  3. Experiments
  4. Results
  5. Discussion and Conclusions

Figures (2)

  • Figure 1: High-level overview of the proposed FairQuant framework (top pathway) illustrating the group importance calculation based on a calibration set, which is then used to allocate appropriate bit widths to the weights. Regular post-training quantization (bottom pathway).
  • Figure 2: Ablations and stability for BAQ. Left: sweep of the bitrate regularizer $\lambda_{\mathrm{baq},b}$ showing test AvgAcc and EOpp on Fitzpatrick17k and ISIC2019. Middle: sweep of the fairness-loss scale $\lambda_{\mathrm{fair}}$ on the ResNet-18 backbone. Right: learning-rate sweep for BAQ bit proxies. All panels use a fixed BAQ bit interval $[b_{\min},b_{\max}]~=[4,16]$. Shaded regions indicate variability across repeated runs.