Hyperbolic Generative Adversarial Network

10 Feb 2021  ·  Diego Lazcano, Nicolás Fredes, Werner Creixell ·

Recently, Hyperbolic Spaces in the context of Non-Euclidean Deep Learning have gained popularity because of their ability to represent hierarchical data. We propose that it is possible to take advantage of the hierarchical characteristic present in the images by using hyperbolic neural networks in a GAN architecture. In this study, different configurations using fully connected hyperbolic layers in the GAN, CGAN, and WGAN are tested, in what we call the HGAN, HCGAN, and HWGAN, respectively. The results are measured using the Inception Score (IS) and the Fr\'echet Inception Distance (FID) on the MNIST dataset. Depending on the configuration and space curvature, better results are achieved for each proposed hyperbolic versions than their euclidean counterpart.

PDF Abstract

Datasets


Results from the Paper


Ranked #4 on Image Generation on MNIST (FID metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Generation MNIST HypGAN FID 7.87 # 4

Methods