Certified Quantization Strategy Synthesis for Neural Networks
File version
Version of Record (VoR)
Author(s)
Chen, G
Song, F
Sun, J
Dong, JS
Griffith University Author(s)
Primary Supervisor
Other Supervisors
Editor(s)
Date
Size
File type(s)
Location
Milan, Italy
Abstract
Quantization plays an important role in deploying neural networks on embedded, real-time systems with limited computing and storage resources (e.g., edge devices). It significantly reduces the model storage cost and improves inference efficiency by using fewer bits to represent the parameters. However, it was recently shown that critical properties may be broken after quantization, such as robustness and backdoor-freeness. In this work, we introduce the first method for synthesizing quantization strategies that verifiably maintain desired properties after quantization, leveraging a key insight that quantization leads to a data distribution shift in each layer. We propose to compute the preimage for each layer based on which the preceding layer is quantized, ensuring that the quantized reachable region of the preceding layer remains within the preimage. To tackle the challenge of computing the exact preimage, we propose an MILP-based method to compute its under-approximation. We implement our method into a tool Quadapter and demonstrate its effectiveness and efficiency by providing certified quantization that successfully preserves model robustness and backdoor-freeness.
Journal Title
Conference Title
Formal Methods: 26th International Symposium, FM 2024, Milan, Italy, September 9–13, 2024, Proceedings, Part I
Book Title
Edition
Volume
14933
Issue
Thesis Type
Degree Program
School
Publisher link
Patent number
Funder(s)
Grant identifier(s)
Rights Statement
Rights Statement
© The Author(s) 2025. Open Access This chapter is licensed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made. The images or other third party material in this chapter are included in the chapter’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the chapter’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.
Item Access Status
Note
Access the data
Related item(s)
Subject
Neural networks
Machine learning
Information and computing sciences
Persistent link to this record
Citation
Zhang, Y; Chen, G; Song, F; Sun, J; Dong, JS, Certified Quantization Strategy Synthesis for Neural Networks, Formal Methods: 26th International Symposium, FM 2024, Milan, Italy, September 9–13, 2024, Proceedings, Part I, 2025, 14933, pp. 343-362