郑州大学学报（工学版）2026，Vol.47Issue(5)：58-67,10.DOI:10.13705/j.issn.1671-6833.2026.02.007
可微分神经网络架构搜索综述
Overview of Differentiable Neural Network Architecture Search
摘要
Abstract
Neural Architecture Search(NAS)was an interdisciplinary study in the field of deep learning,which aimed to automate the design of neural network structures.NAS required repeated training and evaluation of a large number of candidate networks,which was computationally expensive.Differentiable Neural Architecture Search(DNAS)transformed the discrete architecture search problem into a differentiable continuous optimization problem,which reduced the computational cost.Firstly,a search algorithm framework for differentiable network architecture was constructed from three aspects:search space,search strategy and performance evaluation strategy.Secondly,the performance estimation bias,architecture overfitting and search stability problems of parameterization operation,as well as the improvement strategies of optimizing search space and improving efficiency were analyzed,compared and summarized.Then,the error rate,parameter quantity,search time and experimental hardware conditions of typical DNAS algorithms on image classification datasets were compared and analyzed.Finally,it pointed out the application potential of DNAS in complex scenarios such as edge device deployment,medical signal analysis,and cross-modal matching,and proposed future research directions toward multi-objective optimization,task-driven search space design,and cross-task transfer and reuse.关键词
神经网络架构搜索/深度学习/可微分神经网络架构搜索/连续优化/性能估计Key words
neural architecture search/deep learning/differentiable neural architecture search/continuous optimi-zation/performance estimation分类
信息技术与安全科学引用本文复制引用
逯鹏,李科研,张宏坡,陈立伟,武家辉,刘帅兵..可微分神经网络架构搜索综述[J].郑州大学学报（工学版）,2026,47(5):58-67,10.基金项目
国家自然科学基金资助项目(62373330) （62373330）
河南省重点研发计划资助项目(261111210700) （261111210700）
河南省高等学校重点科研项目(25A520022) （25A520022）
