The effectiveness of Evolutionary Neural Architecture Search (ENAS) is influenced by the design of the search space. Nevertheless, common methods including the global search space, scalable search space and hierarchical search space have certain limitations. Specifically, the global search space requires a significant amount of computational resources and time, the scalable search space sacrifices the diversity of network structures and the hierarchical search space increases the search cost in exchange for network diversity. To address above limitation, we propose a novel paradigm of searching neural network architectures and design the Multiple Population Alternate Evolution Neural Architecture Search (MPAE), which can achieve module diversity with a smaller search cost. MPAE converts the search space into L interconnected units and sequentially searches the units, then the above search of the entire network be cycled several times to reduce the impact of previous units on subsequent units. To accelerate the population evolution process, we also propose the the population migration mechanism establishes an excellent migration archive and transfers the excellent knowledge and experience in the migration archive to new populations. The proposed method requires only 0.3 GPU days to search a neural network on the CIFAR dataset and achieves the state-of-the-art results.
Variable Population Memetic Search: A Case Study on the Critical Node Problem
East China University of Science and Technology（华东理工大学）；Université d’Angers（昂热大学）；Institut Universitaire de France（法兰西大学研究院）；The Chinese University of Hong Kong（香港中文大学）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）；Nanjing University of Posts and Telecommunications（南京邮电大学）
A Multi-objective Evolutionary Algorithm Based on Bi-population with Uniform Sampling for Neural Architecture Search
Nanjing University of Information Science and Technology（南京信息工程大学）；China University of Mining and Technology（中国矿业大学）；The Hong Kong Polytechnic University（香港理工大学）；Macau University of Science and Technology（澳门科技大学）；Qingdao University of Science and Technology（青岛科技大学）
A Pairwise Comparison Relation-assisted Multi-objective Evolutionary Neural Architecture Search Method with Multi-population Mechanism
School of Software, Nanjing University of Information Science and Technology（南京信息工程大学软件学院）；Department of Electrical and Computer Engineering, New Jersey Institute of Technology（新泽西理工学院电子与计算机工程系）；RIKEN Center for Computational Science (R-CCS)（日本计算科学中心（R-CCS））；Department of Computing Sciences, Tampere University（塔尔基大学计算机科学系）
Frequent Itemset-driven Search for Finding Minimum Node Separators in Complex Networks
Sino-US Global Logistics Institute, Shanghai Jiao Tong University（上海交通大学中美物流研究院）；Macau Institute of System Engineering, Macau University of Science and Technology（澳门科技大学澳门系统工程研究所）；East China University of Science and Technology（华东理工大学）；Antai College of Economics and Management, Shanghai Jiao Tong University（上海交通大学安泰经济与管理学院）；New Jersey Institute of Technology（新泽西理工学院）
