标杆管理
计算机科学
模块化设计
可用性
建筑
人工神经网络
进化计算
进化算法
人工智能
计算
机器学习
计算机工程
作者
Xiangning Xie,Yuqiao Liu,Yanan Sun,Gary G. Yen,Bing Xue,Mengjie Zhang
标识
DOI:10.1109/tevc.2022.3147526
摘要
Neural architecture search (NAS), which automatically designs the architectures of deep neural networks, has achieved breakthrough success over many applications in the past few years. Among different classes of NAS methods, evolutionary computation based NAS (ENAS) methods have recently gained much attention. Unfortunately, the development of ENAS is hindered by unfair comparison between different ENAS algorithms due to different training conditions and high computational cost caused by expensive performance evaluation. This paper develops a platform named BenchENAS, in short for Benchmarking Evolutionary Neural Architecture Search, to address these issues. BenchENAS makes it easy to achieve fair comparisons between different algorithms by keeping them under the same settings. To accelerate the performance evaluation in a common lab environment, BenchENAS designs a novel and generic efficient evaluation method for the population characteristics of evolutionary computation. This method has greatly improved the efficiency of the evaluation. Furthermore, BenchENAS is easy to install and highly configurable and modular, which brings benefits in good usability and easy extensibility. The paper conducts efficient comparison experiments on eight ENAS algorithms with high GPU utilization on this platform. The experiments validate that the fair comparison issue does exist in the current ENAS algorithms, and BenchENAS can alleviate this issue. A website has been built to promote BenchENAS at https://benchenas.com, where interested researchers can obtain the source code and document of BenchENAS for free.
科研通智能强力驱动
Strongly Powered by AbleSci AI