RT Conference Proceedings
T1 Spatial evolutionary generative adversarial networks.
A1 Toutouh-el-Alamin, Jamal
A1 Hemberg, Erik
A1 O'Reilly, Una-May
K1 Redes neuronales (Informática)
K1 Computación evolutiva
K1 Algoritmos computacionales
AB Generative adversary networks (GANs) suffer from training pathologies such as instability and mode collapse. These pathologies mainly arise from a lack of diversity in their adversarial interactions. Evolutionary generative adversarial networks apply the principles of evolutionary computation to mitigate these problems. We hybridize two of these approaches that promote training diversity. One, E-GAN, at each batch, injects mutation diversity by training the (replicated) generator with three independent objective functions then selecting the resulting best performing generator for the next batch. The other, Lipizzaner, injects population diversity by training a two-dimensional grid of GANs with a distributed evolutionary algorithm that includes neighbor exchanges of additional training adversaries, performance based selection and population-based hyper-parameter tuning. We propose to combine mutation and population approaches to diversity improvement. We contribute a superior evolutionary GANs training method, Mustangs, that eliminates the single loss function used across Lipizzaner's grid. Instead, each training round, a loss function is selected with equal probability, from among the three E-GAN uses. Experimental analyses on standard benchmarks, MNIST and CelebA, demonstrate that Mustangs provides a statistically faster training method resulting in more accurate networks.
PB ACM
YR 2019
FD 2019-07-13
LK https://hdl.handle.net/10630/32618
UL https://hdl.handle.net/10630/32618
LA eng
NO Toutouh, J., Hemberg, E., & O'Reilly, U. M. (2019, July). Spatial evolutionary generative adversarial networks. In Proceedings of the genetic and evolutionary computation conference (pp. 472-480). DOI: 10.1145/2001858.2002076
NO Política de acceso abierto tomada de: https://www.acm.org/publications/openaccess#h-green-open-access
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 15 abr 2026