Examination of the Multimodal Nature of Multi-Objective Neural Architecture Search

Cheng Gong1; Yang Nan1; Lie Meng Pang1; Hisao Ishibuchi1; Qingfu Zhang2

10.1109/SSCI52147.2023.10372012

2023

2770-0097

978-1-6654-3064-7

2023 IEEE Symposium Series on Computational Intelligence (SSCI)

1821-1828

5-8 Dec. 2023

Mexico City, Mexico

Remarkable successes in deep learning have spurred significant growth in the field of neural architecture search (NAS), which is rapidly advancing as a promising technique for automating the design of network architecture. From an optimization standpoint, a NAS task for a given search space can be viewed as a multi-objective optimization problem (MOP) when considering multiple design criteria simultaneously (e.g., prediction accuracy, architecture complexity, hardware efficiency). However, whether a NAS problem is a multimodal multi-objective optimization problem or not (i.e., whether a single non-dominated solution in the objective space has multiple different neural network architectures or not) has not been examined in the literature. This presents an intriguing research question that merits further investigation. To fill this gap, we examine the multimodal nature of seven multi-objective NAS problems. By doing so, this work aims to help MOP researchers to better understand the characteristics of the multi-objective NAS problems.

Neural architecture search Multi-objective optimization Multimodal multi-objective optimization

第一

EI

20240415441985

IEEE

1.Department of Computer Science and Engineering, Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation, Southern University of Science and Technology, Shenzhen, China
2.Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong

Cheng Gong,Yang Nan,Lie Meng Pang,et al. Examination of the Multimodal Nature of Multi-Objective Neural Architecture Search[C],2023:1821-1828.