Neural Architecture Search for Text Classification With Limited Computing Resources Using Efficient Cartesian Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.7810

@Article{Wu_Xuan:ieeeTEC,

• author = "Xuan Wu and Di Wang and Huanhuan Chen and Lele Yan and Yubin Xiao and Chunyan Miao and Hongwei Ge and Dong Xu and Yanchun Liang and Kangping Wang and Chunguo Wu and You Zhou",
• title = "Neural Architecture Search for Text Classification With Limited Computing Resources Using Efficient Cartesian Genetic Programming",
• journal = "IEEE Transactions on Evolutionary Computation",
• year = "2024",
• volume = "28",
• number = "3",
• pages = "638--652",
• month = jun,
• keywords = "genetic algorithms, genetic programming, Cartesian Genetic Programming, ANN, neural architecture search, text classification, evolutionary strategy",
• ISSN = "1089-778X",
• DOI = "doi:10.1109/TEVC.2023.3346969",
• abstract = "...proposes a crossover operator, a light-weighted age mechanism, and two adaptive mutation operators as the novel components in our efficient CGP (ECGP) method. To assess the performance of ECGP, we conduct extensive experiments on three text classification task datasets. The experimental results demonstrate that ECGP outperforms other NAS methods, requiring only hundreds of fitness evaluations to find architectures with competitive accuracy compared with human-designed models. Additionally, the ECGP-evolved architectures are shown as converging fast and stably, and having high-level transferability with merely a one to two percent accuracy drop. Ablation studies demonstrate the effectiveness of the proposed operators and age mechanism, and identify GRU as the most critical function in the text classification task. Finally, we summarise three design principles observed from the ECGP-evolved architectures that are in line with human-design strategies.",
• notes = "also known as \cite{10373942} See \cite{DBLP:journals/corr/abs-2103-07173}",

}

Genetic Programming entries for Xuan Wu Di Wang Huanhuan Chen Lele Yan Yubin Xiao Chunyan Miao Hongwei Ge Dong Xu Yanchun Liang Kangping Wang Chunguo Wu You Zhou

Citations