Year: 2022
Type: conference-paper
Abstract: Performance estimation of neural architecture is a crucial component of neural architecture search (NAS). Meanwhile, neural predictor is a current mainstream performance estimation method. However, it is a challenging task to train the predictor with few architecture evaluations for efficient NAS. In this paper, we propose a graph masked autoencoder (GMAE) enhanced predictor, which can reduce the dependence on supervision data by self-supervised pre-training with untrained architectures. We compare our GMAE-enhanced predictor with existing predictors in different search spaces, and experimental results show that our predictor has high query utilization. Moreover, GMAE-enhanced predictor with different search strategies can discover competitive architectures in different search spaces. Code and supplementary materials are available at https://github.com/kunjing96/GMAENAS.git.
Authors: Kun Jing, Jungang Xu, Pengfei Li
Institution: University of Chinese Academy of Sciences
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4285600331