自适应策略优化的粒子群优化算法在神经网络架构搜索中的应用  

Application of adaptive strategy optimizied particle swarm optimization algorithm in neural network architecture search

作　　者：程金芮 金瑾 张朝龙[1] 孔超 何嘉[3] 张鑫[4] CHENG Jinrui;JIN Jin;ZHANG Chaolong;KONG Chao;HE Jia;ZHANG Xin(School of Software Engineering,Chengdu University of Information Technology,Chengdu Sichuan 610225,China;School of Computing and Engineering,University of Huddersfield,Huddersfield HD1,Huddersfield West Jorkshire HD13DH,UK;School of Computer Science,Chengdu University of Information Technology,Chengdu Sichuan 610225,China;Government,Enterprise and Industry R&D Division,Software Research Institute,China United Network Communications Company Limited,Harbin Heilongjiang 150006,China)

机构地区：[1]成都信息工程大学软件工程学院,成都610225 [2]哈德斯菲尔德大学计算机与工程学院,英国西约克郡哈德斯菲尔德HD13DH [3]成都信息工程大学计算机学院,成都610225 [4]中国联合网络通信有限公司软件研究院政企与行业研发事业部,哈尔滨150006

出　　处：《计算机应用》2024年第S01期60-64,共5页journal of Computer Applications

基　　金：四川省科技厅创新人才支持计划项目(2020JDR0330)。

摘　　要：针对神经网络架构搜索(NAS)任务,提出一种自适应重启策略驱动的协作学习粒子群优化(ARCLPSO)算法。算法核心流程包括协作学习与信息共享、策略切换和参数自适应,以改进传统粒子群优化(PSO)算法在NAS中的性能。ARCLPSO算法结合了全局与局部信息的协同作用和智能切换学习策略。具体地,ARCLPSO利用全局和局部信息的协同作用令粒子向更优的方向移动,通过智能的切换粒子学习策略平衡粒子的搜索性能和收敛速度,提高搜索速度和搜索质量。在NAS-Bench-101数据集上的实验结果表明,ARCLPSO的收敛时间相较于传统进化算法(REA)和随机搜索(RS),分别减少了40.9%和55.2%。Aiming at the Neural Architecture Search(NAS)task,an Auto-Reset Cooperative Learning Particle Swarm Optimization(ARCLPSO)algorithm,driven by an adaptive restart strategy,was proposed.The core process included cooperative learning and information sharing,strategy switching,and parameter adaptation to improve the performance of the traditional PSO(Particle Swarm Optimization)algorithm in NAS.Specifically,the synergies between global and local information were leveraged to steer particles towards a more optimal trajectory.Particle learning strategies were dynamically shifted to balance search performance and convergence speed,thereby augmenting both search speed and quality.Experimental results on the NAS-Bench-101 dataset demonstrate that compared to traditional Regular Evolutionary Algorithm(REA)and Random Search(RS),the convergence time of ARCLPSO reduces by 40.9%and 55.2%.

关 键 词：神经网络架构搜索 粒子群优化 进化算法 NAS-Bench-101 自适应的协作学习算法 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]