# Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search

arXiv: https://arxiv.org/abs/2010.04354 · HTML: https://mlsanity.com/paper/2010.04354/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Oct 2020.

## Built on by (most cited first, 26 of 26)

- [Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models](https://mlsanity.com/paper/2209.13325/) (2022)
- [QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization](https://mlsanity.com/paper/2203.05740/) (2022)
- [Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling](https://mlsanity.com/paper/2304.09145/) (2023)
- [MQBench: Towards Reproducible and Deployable Model Quantization Benchmark](https://mlsanity.com/paper/2111.03759/) (2021)
- [Synergistic Self-supervised and Quantization Learning](https://mlsanity.com/paper/2207.05432/) (2022)
- [EQ-Net: Elastic Quantization Neural Networks](https://mlsanity.com/paper/2308.07650/) (2023)
- [Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning Approach](https://mlsanity.com/paper/2207.10188/) (2022)
- [TEQ: Trainable Equivalent Transformation for Quantization of LLMs](https://mlsanity.com/paper/2310.10944/) (2023)
- [QuantNAS for super resolution: searching for efficient quantization-friendly architectures against quantization noise](https://mlsanity.com/paper/2208.14839/) (2022)
- [Vertical Layering of Quantized Neural Networks for Heterogeneous Inference](https://mlsanity.com/paper/2212.05326/) (2022)
- [FlattenQuant: Breaking Through the Inference Compute-bound for Large Language Models with Per-tensor Quantization](https://mlsanity.com/paper/2402.17985/) (2024)
- [Outlier-Aware Post-Training Quantization for Image Super-Resolution](https://mlsanity.com/paper/2511.00682/) (2025)
- [Efficient Adaptive Activation Rounding for Post-Training Quantization](https://mlsanity.com/paper/2208.11945/) (2022)
- [On the Impact of Black-box Deployment Strategies for Edge AI on Latency and Model Performance](https://mlsanity.com/paper/2403.17154/) (2024)
- [TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision](https://mlsanity.com/paper/2506.11431/) (2025)
- [Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Survey](https://mlsanity.com/paper/2208.10498/) (2022)
- [SpaceEvo: Hardware-Friendly Search Space Design for Efficient INT8 Inference](https://mlsanity.com/paper/2303.08308/) (2023)
- [In-Distribution Consistency Regularization Improves the Generalization of Quantization-Aware Training](https://mlsanity.com/paper/2402.13497/) (2024)
- [Mixed-precision Supernet Training from Vision Foundation Models using Low Rank Adapter](https://mlsanity.com/paper/2403.20080/) (2024)
- [Error Diffusion: Post Training Quantization with Block-Scaled Number Formats for Neural Networks](https://mlsanity.com/paper/2410.11203/) (2024)
- [On the Impact of White-box Deployment Strategies for Edge AI on Latency and Model Performance](https://mlsanity.com/paper/2411.00907/) (2024)
- [Efficient Quantization-Aware Training on Segment Anything Model in Medical Images and Its Deployment](https://mlsanity.com/paper/2412.11186/) (2024)
- [Onboard Optimization and Learning: A Survey](https://mlsanity.com/paper/2505.08793/) (2025)
- [Nearly Lossless Adaptive Bit Switching](https://mlsanity.com/paper/2502.01199/) (2025)
- [pQuant: Towards Effective Low-Bit Language Models via Decoupled Linear Quantization-Aware Training](https://mlsanity.com/paper/2602.22592/) (2026)
- [Device-Conditioned Neural Architecture Search for Efficient Robotic Manipulation](https://mlsanity.com/paper/2604.10170/) (2026)

## Abstract (arXiv)

Quantization Neural Networks (QNN) have attracted a lot of attention due to their high efficiency. To enhance the quantization accuracy, prior works mainly focus on designing advanced quantization algorithms but still fail to achieve satisfactory results under the extremely low-bit case. In this work, we take an architecture perspective to investigate the potential of high-performance QNN. Therefore, we propose to combine Network Architecture Search methods with quantization to enjoy the merits of the two sides. However, a naive combination inevitably faces unacceptable time consumption or unstable training problem. To alleviate these problems, we first propose the joint training of architecture and quantization with a shared step size to acquire a large number of quantized models. Then a bit-inheritance scheme is introduced to transfer the quantized models to the lower bit, which further reduces the time cost and meanwhile improves the quantization accuracy. Equipped with this overall framework, dubbed as Once Quantization-Aware Training~(OQAT), our searched model family, OQATNets, achieves a new state-of-the-art compared with various architectures under different bit-widths. In particular, OQAT-2bit-M achieves 61.6% ImageNet Top-1 accuracy, outperforming 2-bit counterpart MobileNetV3 by a large margin of 9% with 10% less computation cost. A series of quantization-friendly architectures are identified easily and extensive analysis can be made to summarize the interaction between quantization and neural architectures. Codes and models are released at https://github.com/LaVieEnRoseSMZ/OQA