BenchENAS: A Benchmarking Platform for Evolutionary Neural Architecture Search

TL;DR

BenchENAS is a new benchmarking platform designed to enable fair, efficient, and reproducible comparisons of evolutionary neural architecture search algorithms, addressing current limitations in evaluation methods and platform support.

Contribution

This paper introduces BenchENAS, a modular, easy-to-use platform that standardizes evaluation environments and improves efficiency for ENAS algorithms.

Findings

BenchENAS enables fair comparison of eight ENAS algorithms.

The platform achieves high GPU utilization during experiments.

BenchENAS alleviates issues of inconsistent evaluation environments.

Abstract

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 issues of fair comparisons and efficient evaluations have hindered the development of ENAS. The current benchmark architecture datasets designed for fair comparisons only provide the datasets, not the ENAS algorithms or the platform to run the algorithms. The existing efficient evaluation methods are either not suitable for the population-based ENAS algorithm or are too complex to use. This paper develops a platform named BenchENAS to address these issues. BenchENAS aims to achieve fair comparisons by running different algorithms in the same environment and with the same settings. To achieve efficient evaluation in a common lab environment, BenchENAS designs a parallel component and a cache component with high maintainability. 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, 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.