# Quantization Meets OOD: Generalizable Quantization-aware Training from a Flatness Perspective

Source: [Quantization Meets OOD: Generalizable Quantization-aware Training from a Flatness Perspective](<https://www.sota2.com/research/paper/68fa7b2c1e209131cea87014>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:34:43.561Z

Authors: Jiacheng Jiang, Yuan Meng, Chen Tang, Han Yu, Qun Li, Zhi Wang, Wenwu Zhu

Published: 2025-08-31T14:05:14.000Z

## Abstract

Current quantization-aware training (QAT) methods primarily focus on enhancing the performance of quantized models on in-distribution (I.D) data, while overlooking the potential performance degradation on out-of-distribution (OOD) data. In this paper, we first substantiate this problem through rigorous experiment, showing that QAT can lead to a significant OOD generalization performance degradation. Further, we find the contradiction between the perspective that flatness of loss landscape gives rise to superior OOD generalization and the phenomenon that QAT lead to a sharp loss landscape, can cause the above problem. Therefore, we propose a flatness-oriented QAT method, FQAT, to achieve generalizable QAT. Specifically, i) FQAT introduces a layer-wise freezing mechanism to mitigate the gradient conflict issue between dual optimization objectives (i.e., vanilla QAT and flatness). ii) FQAT proposes an disorder-guided adaptive freezing algorithm to dynamically determines which layers to freeze at each training step, effectively addressing the challenges caused by interference between layers. A gradient disorder metric is designed to help the algorithm identify unstable layers during training. Extensive experiments on influential OOD benchmark demonstrate the superiority of our method over state-of-the-art baselines under both I.D and OOD image classification tasks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.00859>)

[PDF](<https://arxiv.org/pdf/2509.00859.pdf>)
