GEGAN: gradient-guided evolutionary framework for GAN optimization

Wenwen Jia

doi:10.1016/j.eswa.2026.131257

GEGAN: gradient-guided evolutionary framework for GAN optimization

2026-01-28

0

PRE

AI

DOI：10.1016/j.eswa.2026.131257

原文链接

原文求助

摘要

En 中文

• Proposes a gradient-guided mutation operator to enhance GAN output quality and diversity. • Utilizes gradient information to accelerate generator convergence and improve training stability. • Develops GEGAN with proven convergence under general conditions and an acceptance-based strategy. • Empirically validates GEGAN’s superiority in data-scarce, multi-class, and noisy environments.

GEGAN: gradient-guided evolutionary framework for GAN optimization

摘要

期刊

机构