Timezone: »

PacGAN: The power of two samples in generative adversarial networks
Zinan Lin · Ashish Khetan · Giulia Fanti · Sewoong Oh

Tue Dec 04 07:45 AM -- 09:45 AM (PST) @ Room 210 #22

Generative adversarial networks (GANs) are a technique for learning generative models of complex data distributions from samples. Despite remarkable advances in generating realistic images, a major shortcoming of GANs is the fact that they tend to produce samples with little diversity, even when trained on diverse datasets. This phenomenon, known as mode collapse, has been the focus of much recent work. We study a principled approach to handling mode collapse, which we call packing. The main idea is to modify the discriminator to make decisions based on multiple samples from the same class, either real or artificially generated. We draw analysis tools from binary hypothesis testing---in particular the seminal result of Blackwell---to prove a fundamental connection between packing and mode collapse. We show that packing naturally penalizes generators with mode collapse, thereby favoring generator distributions with less mode collapse during the training process. Numerical experiments on benchmark datasets suggest that packing provides significant improvements.

Author Information

Zinan Lin (Carnegie Mellon University)
Ashish Khetan (Amazon AI Labs)
Giulia Fanti (CMU)
Sewoong Oh (University of Washington)

More from the Same Authors