Host-Pathongen Co-evolution Inspired Algorithm Enables Robust GAN Training

by   Andrei Kucharavy, et al.

Generative adversarial networks (GANs) are pairs of artificial neural networks that are trained one against each other. The outputs from a generator are mixed with the real-world inputs to the discriminator and both networks are trained until an equilibrium is reached, where the discriminator cannot distinguish generated inputs from real ones. Since their introduction, GANs have allowed for the generation of impressive imitations of real-life films, images and texts, whose fakeness is barely noticeable to humans. Despite their impressive performance, training GANs remains to this day more of an art than a reliable procedure, in a large part due to training process stability. Generators are susceptible to mode dropping and convergence to random patterns, which have to be mitigated by computationally expensive multiple restarts. Curiously, GANs bear an uncanny similarity to a co-evolution of a pathogen and its host's immune system in biology. In a biological context, the majority of potential pathogens indeed never make it and are kept at bay by the hots' immune system. Yet some are efficient enough to present a risk of a serious condition and recurrent infections. Here, we explore that similarity to propose a more robust algorithm for GANs training. We empirically show the increased stability and a better ability to generate high-quality images while using less computational power.


Guiding GANs: How to control non-conditional pre-trained GANs for conditional image generation

Generative Adversarial Networks (GANs) are an arrange of two neural netw...

SGAN: An Alternative Training of Generative Adversarial Networks

The Generative Adversarial Networks (GANs) have demonstrated impressive ...

Fictitious GAN: Training GANs with Historical Models

Generative adversarial networks (GANs) are powerful tools for learning g...

Don't Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance

Generative adversarial networks (GANs) have received an upsurging intere...

Understanding and Stabilizing GANs' Training Dynamics with Control Theory

Generative adversarial networks (GANs) have made significant progress on...

Shared Loss between Generators of GANs

Generative adversarial networks are generative models that are capable o...

Using Skill Rating as Fitness on the Evolution of GANs

Generative Adversarial Networks (GANs) are an adversarial model that ach...

Please sign up or login with your details

Forgot password? Click here to reset