Semi-Supervised Learning with IPM-based GANs: an Empirical Study
Abstract
We present an empirical investigation of a recent class of Generative Adversarial Networks (GANs) using Integral Probability Metrics (IPM) and their performance for semi-supervised learning. IPM-based GANs like Wasserstein GAN, Fisher GAN and Sobolev GAN have desirable properties in terms of theoretical understanding, training stability, and a meaningful loss. In this work we investigate how the design of the critic (or discriminator) influences the performance in semi-supervised learning. We distill three key take-aways which are important for good SSL performance: (1) the K+1 formulation, (2) avoiding batch normalization in the critic and (3) avoiding gradient penalty constraints on the classification layer.
Cite
@article{arxiv.1712.02505,
title = {Semi-Supervised Learning with IPM-based GANs: an Empirical Study},
author = {Tom Sercu and Youssef Mroueh},
journal= {arXiv preprint arXiv:1712.02505},
year = {2017}
}
Comments
Appeared at NIPS 2017 Workshop: Deep Learning: Bridging Theory and Practice