Is quantum optimization ready? An effort towards neural network compression using adiabatic quantum computing

doi:10.1016/j.future.2025.107908

	Is quantum optimization ready? An effort towards neural network compression using adiabatic quantum computing
	Wang, Zhehui 1; Choong, Benjamin Chen Ming 1; Huang, Tian 2; Gerlinghoff, Daniel 1; Goh, Rick Siow Mong 1; Liu, Cheng 3; Luo, Tao 1
	2026
发表期刊	FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
ISSN	0167-739X
卷号	174 页码:11
摘要	Quantum optimization is the most mature quantum computing technology to date, providing a promising approach towards efficiently solving complex combinatorial problems. Methods such as adiabatic quantum computing (AQC) have been employed in recent years on important optimization problems across various domains. In deep learning, deep neural networks (DNN) have reached immense sizes to support new predictive capabilities. Optimization of large-scale models is critical for sustainable deployment, but becomes increasingly challenging with ever-growing model sizes and complexity. While quantum optimization is suitable for solving complex problems, its application to DNN optimization is not straightforward, requiring thorough reformulation for compatibility with commercially available quantum devices. In this work, we explore the potential of adopting AQC for fine-grained pruning-quantization of convolutional neural networks. We rework established heuristics to formulate model compression as a quadratic unconstrained binary optimization (QUBO) problem, and assess the solution space offered by commercial quantum annealing devices. Through our exploratory efforts of reformulation, we demonstrate that AQC can achieve effective compression of practical DNN models. Experiments demonstrate that adiabatic quantum computing (AQC) not only outperforms classical algorithms like genetic algorithms and reinforcement learning in terms of time efficiency but also excels at identifying global optima.
关键词	Adiabatic quantum computing Quantum annealing Neural network optimization Model compression
DOI	10.1016/j.future.2025.107908
收录类别	SCI
语种	英语
资助项目	National Research Foundation Singapore, under its Quantum Engineering Programme 2.0 (National Quantum Computing Hub)[NRF2021-QEP2-02-P01] ; A*STAR[C230917003]
WOS研究方向	Computer Science
WOS类目	Computer Science, Theory & Methods
WOS记录号	WOS:001511454300003
出版者	ELSEVIER
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42362
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Luo, Tao
作者单位	1.ASTAR, Inst High Performance Comp IHPC, 1 Fusionopolis Way,16-16 Connexis, Singapore 138632, Singapore 2.Huadian Coal Ind Grp Co Ltd, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Wang, Zhehui,Choong, Benjamin Chen Ming,Huang, Tian,et al. Is quantum optimization ready? An effort towards neural network compression using adiabatic quantum computing[J]. FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE,2026,174:11.
APA	Wang, Zhehui.,Choong, Benjamin Chen Ming.,Huang, Tian.,Gerlinghoff, Daniel.,Goh, Rick Siow Mong.,...&Luo, Tao.(2026).Is quantum optimization ready? An effort towards neural network compression using adiabatic quantum computing.FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE,174,11.
MLA	Wang, Zhehui,et al."Is quantum optimization ready? An effort towards neural network compression using adiabatic quantum computing".FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 174(2026):11.