Generative Adversarial Network Training is a Continual Learning Problem

Kevin J Liang, Chunyuan Li, Guoyin Wang, Lawrence Carin

Abstract: Generative Adversarial Networks (GANs) have proven to be a powerful framework for learning to draw samples from complex distributions. However, GANs are also notoriously difficult to train, with mode collapse and oscillations a common problem. We hypothesize that this is at least in part due to the evolution of the generator distribution and the catastrophic forgetting tendency of neural networks, which leads to the discriminator losing the ability to remember synthesized samples from previous instantiations of the generator. Recognizing this, our contributions are twofold. First, we show that GAN training makes for a more interesting and realistic benchmark for continual learning methods evaluation than some of the more canonical datasets. Second, we propose leveraging continual learning techniques to augment the discriminator, preserving its ability to recognize previous generator samples. We show that the resulting methods add only a light amount of computation, involve minimal changes to the model, and result in better overall performance on the examined image and text generation tasks.

Keywords: Generative Adversarial Networks, Continual Learning, Deep Learning

TL;DR: Generative Adversarial Network Training is a Continual Learning Problem.

Data: [COCO Captions](https://paperswithcode.com/dataset/coco-captions)

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:1811.11083/code)