基于突触流的神经结构搜索加速基因库最优混合进化算法

Proceedings of the Companion Conference on Genetic and Evolutionary Computation Pub Date : 2023-07-15 DOI:10.1145/3583133.3596438

Khoa Huu Tran, Luc Truong, An Vo, N. H. Luong

{"title":"基于突触流的神经结构搜索加速基因库最优混合进化算法","authors":"Khoa Huu Tran, Luc Truong, An Vo, N. H. Luong","doi":"10.1145/3583133.3596438","DOIUrl":null,"url":null,"abstract":"This study experiments the integration of the zero-cost proxy metric Synaptic Flow with the Gene-pool Optimal Mixing (GOM) crossover to efficiently generate new candidates during an evolutionary neural architecture search (ENAS). Our experiments demonstrate that the Gene-pool Optimal Mixing Evolutionary Algorithm (GOMEA) with Synaptic Flow can obtain top-performing architectures with a small additional overhead compared to a classic Genetic Algorithm. Code is available at: https://github.com/ELO-Lab/SF-GOMENAS.","PeriodicalId":422029,"journal":{"name":"Proceedings of the Companion Conference on Genetic and Evolutionary Computation","volume":"2005 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Accelerating Gene-pool Optimal Mixing Evolutionary Algorithm for Neural Architecture Search with Synaptic Flow\",\"authors\":\"Khoa Huu Tran, Luc Truong, An Vo, N. H. Luong\",\"doi\":\"10.1145/3583133.3596438\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This study experiments the integration of the zero-cost proxy metric Synaptic Flow with the Gene-pool Optimal Mixing (GOM) crossover to efficiently generate new candidates during an evolutionary neural architecture search (ENAS). Our experiments demonstrate that the Gene-pool Optimal Mixing Evolutionary Algorithm (GOMEA) with Synaptic Flow can obtain top-performing architectures with a small additional overhead compared to a classic Genetic Algorithm. Code is available at: https://github.com/ELO-Lab/SF-GOMENAS.\",\"PeriodicalId\":422029,\"journal\":{\"name\":\"Proceedings of the Companion Conference on Genetic and Evolutionary Computation\",\"volume\":\"2005 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-07-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the Companion Conference on Genetic and Evolutionary Computation\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3583133.3596438\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the Companion Conference on Genetic and Evolutionary Computation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3583133.3596438","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

本研究将零成本代理度量Synaptic Flow与基因池最优混合(GOM)交叉相结合，在进化神经结构搜索(ENAS)中有效地生成新的候选对象。我们的实验表明，与经典遗传算法相比，带有Synaptic Flow的基因池最优混合进化算法(gome)可以在很小的额外开销下获得性能最好的架构。代码可从https://github.com/ELO-Lab/SF-GOMENAS获得。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Accelerating Gene-pool Optimal Mixing Evolutionary Algorithm for Neural Architecture Search with Synaptic Flow

This study experiments the integration of the zero-cost proxy metric Synaptic Flow with the Gene-pool Optimal Mixing (GOM) crossover to efficiently generate new candidates during an evolutionary neural architecture search (ENAS). Our experiments demonstrate that the Gene-pool Optimal Mixing Evolutionary Algorithm (GOMEA) with Synaptic Flow can obtain top-performing architectures with a small additional overhead compared to a classic Genetic Algorithm. Code is available at: https://github.com/ELO-Lab/SF-GOMENAS.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Proceedings of the Companion Conference on Genetic and Evolutionary Computation

自引率

0.00%

发文量