Neural architecture search via reference point based multi-objective evolutionary algorithm

doi:10.1016/j.patcog.2022.108962

2022-12-01

PRE

Lyuyang Tong

Bo Du *

DOI：10.1016/j.patcog.2022.108962

原文链接

原文求助

摘要

En 中文

For neural architecture search, NSGA-Net has searched a representative neural architecture set of Pareto-optimal solutions to consider both accuracy and computation complexity simultaneously. However, some decision-makers only concentrate on such neural architectures in the subpart regions of Pareto-optimal Frontier that they have interests in. Under the above circumstances, certain uninterested neural architectures may cost many computing resources. In order to consider the preference of decision-makers, we propose the reference point based NSGA-Net (RNSGA-Net) for neural architecture search. The core of RNSGA-Net adopts the reference point approach to guarantee the Pareto-optimal region close to the reference points and also combines the advantage of NSGAII with the fast nondominated sorting approach to split the Pareto front. Moreover, we augment an extra bit value of the original encoding to represent two types of residual block and one type of dense block for residual connection and dense connection in the RNSGA-Net. In order to satisfy the decision-maker preference, the multi-objective is measured to search competitive neural architecture by minimizing an error metric and FLOPs of computational complexity. Experiment results on the CIFAR-10 dataset demonstrate that RNSGA-Net can improve NSGA-Net in terms of the more structured representation space and the preference of decision-makers. (C) 2022 Elsevier Ltd. All rights reserved.

Keyword:

Neural architecture search

Multi-objective evolutionary algorithm

The image classification

期刊

Pattern Recognition

IF:

7.6

论文数:

1.3W

被引数:

4.5W

机构

wuhan university

学者数:

8.1W

论文数: 5.8W

被引数: 70

引用论文

Wider or Deeper: Revisiting the ResNet Model for Visual Recognition 更广泛或更深入: 重新审视视觉识别的ResNet模型

PATTERN RECOGNITION

IF7.6

2019-06-01

952

OAAI

Wu, Zifeng; Shen, Chunhua; van den Hengel, Anton

Efficient densely connected convolutional neural networks 高效密集连接卷积神经网络

PATTERN RECOGNITION

IF7.6

2021-01-01

PREAI

Li, Guoqing; Zhang, Meng; Li, Jiaojie; Lv, Feng; Tong, Guodong

Completely Automated CNN Architecture Design Based on Blocks 基于块的全自动CNN体系结构设计

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS

IF8.9

2020-04-01

226

OAAI

Sun, Yanan; Xue, Bing; Zhang, Mengjie; Yen, Gary G.

Multiobjective evolutionary algorithms: A survey of the state of the art

SWARM AND EVOLUTIONARY COMPUTATION

IF8.5

2011-03-01

1.8K

PREAI

Zhou, Aimin; Qu, Bo-Yang; Li, Hui; Zhao, Shi-Zheng; Suganthan, Ponnuthurai Nagaratnam; Zhang, Qingfu

Recent advances in convolutional neural networks 卷积神经网络的最新进展

PATTERN RECOGNITION

IF7.6

2018-05-01

3.8K

OAAI

Gu, Jiuxiang; Wang, Zhenhua; Kuen, Jason; Ma, Lianyang; Shahroudy, Amir; Shuai, Bing; Liu, Ting; Wang, Xingxing; Wang, Gang; Cai, Jianfei; Chen, Tsuhan

A fast and elitist multiobjective genetic algorithm: NSGA-II 一种快速而精英的多目标遗传算法: nsga-ii

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION

IF12

2002-04-01

3.5W