Evolutionary Architecture Search for Generative Adversarial Networks Based on Weight Sharing
IEEE Transactions on Evolutionary Computation · 2024-06 · 28 (3) · 653-667
DOI: 10.1109/tevc.2023.3338371 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Evolutionary Computation, 2024-06. Verfasst von Yu Xue und 6 weiteren Autor:innen. Die Arbeit wurde bisher 52-mal zitiert (Crossref) und nennt 62 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province, Natural Science Foundation of the Jiangsu Higher Education Institutions of China.
Abstract (Originalsprache)
Generative adversarial networks (GANs) are a powerful generative technique but frequently face challenges with training stability. Network architecture plays a significant role in determining the final output of GANs, but designing a fine architecture demands extensive domain expertise. This article aims to address this issue by searching for high-performance generator’s architectures through neural architecture search (NAS). The proposed approach, called evolutionary weight sharing GANs (EWSGAN), is based on weight sharing and comprises two steps. First, a supernet of the generator is trained using weight sharing. Second, a multiobjective evolutionary algorithm (MOEA) is employed to identify optimal subnets from the supernet. These subnets inherit weights directly from the supernet for fitness assessment. Two strategies are used to stabilize the training of the generator supernet: 1) a fair single-path sampling strategy and 2) a discarding strategy. Experimental results indicate that the architecture searched by our method achieved a new state-of-the-art among NAS–GAN methods with a Fréchet inception distance (FID) of 9.09 and an inception score (IS) of 8.99 on the CIFAR-10 dataset. It also demonstrates competitive performance on the STL-10 dataset, achieving FID of 21.89 and IS of 10.51.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Jiangsu Province
- Natural Science Foundation of the Jiangsu Higher Education Institutions of China
- Distinguished Professors of Jiangsu Province
Zitieren
APA
Xue, Y., Tong, W., Neri, F., Chen, P., Luo, T., Zhen, L., & Wang, X. (2024). Evolutionary Architecture Search for Generative Adversarial Networks Based on Weight Sharing. IEEE Transactions on Evolutionary Computation, 28(3), 653-667. https://doi.org/10.1109/tevc.2023.3338371
Vancouver
Xue Y, Tong W, Neri F, Chen P, Luo T, Zhen L, et al. Evolutionary Architecture Search for Generative Adversarial Networks Based on Weight Sharing. IEEE Transactions on Evolutionary Computation. 2024;28(3):653-667. doi:10.1109/tevc.2023.3338371
BibTeX
@article{Xue2024,
author = {Xue, Yu and Tong, Weinan and Neri, Ferrante and Chen, Peng and Luo, Tao and Zhen, Liangli and Wang, Xiao},
title = {Evolutionary Architecture Search for Generative Adversarial Networks Based on Weight Sharing},
journal = {IEEE Transactions on Evolutionary Computation},
year = {2024},
volume = {28},
number = {3},
pages = {653--667},
doi = {10.1109/tevc.2023.3338371}
}
EUVIMED