HackerPapers

arXiv:1606.03657cs.LG

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

Xi Chen, Yan Duan, Rein Houthooft, John Schulman, Ilya Sutskever, Pieter Abbeel

Abstract

This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner. InfoGAN is a generative adversarial network that also maximizes the mutual information between a small subset of the latent variables and the observation. We derive a lower bound to the mutual information objective that can be optimized efficiently, and show that our training procedure can be interpreted as a variation of the Wake-Sleep algorithm. Specifically, InfoGAN successfully disentangles writing styles from digit shapes on the MNIST dataset, pose from lighting of 3D rendered images, and background digits from the central digit on the SVHN dataset. It also discovers visual concepts that include hair styles, presence/absence of eyeglasses, and emotions on the CelebA face dataset. Experiments show that InfoGAN learns interpretable representations that are competitive with representations learned by existing fully supervised methods.

arXiv comments
Journal reference
DOI
Subjects
cs.LGMachine Learning stat.MLMachine Learning (Statistics)

On Hacker News

Linked by 5 identifiable commenters in 6 comments across 6 threads, from Jun 2016 to Sep 2017. Found in 1 HN submission from Jul 2016 to Jul 2016. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments6 threads

  1. PassGAN: A Deep Learning Approach for Password Guessing 1 comment

    • I'm assuming by iterate you mean "generate outputs of a GAN which preserve some order that you can iterate through." The answer is yes, but not in the way that one might think. Despite the fact that we seed the GAN with input noise, there is no guarantee that the GAN makes use…

      kdohertyView on HNParent context

  2. Unsupervised sentiment neuron 1 comment

    • The paper I was thinking of is called: "InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets"[0]. I do not have experience training and investigating neural nets, but from what I read in that paper, there's no reason to presume…

      fiterView on HNParent context

  3. Ask HN: What is the most exciting development in your field right now? 1 comment

    • I read the infoGAN paper yesterday. It blew my mind. https://arxiv.org/pdf/1606.03657v1.pdf. This is a way to do disentangled feature representation learning without supervision.

      pinouchonView on HNParent context

  4. Darpa Goes “Meta” with Machine Learning for Machine Learning (2016) 1 comment

    • GANs (and InfoGAN[0] in particular) has shown there are still pretty huge breakthoughs out there. Some other things you may be interested in: Learning to learn by gradient descent by gradient descent[1] Neural Architecture Search with Reinforcement Learning[2] [0]…

      nlView on HNParent context

  5. OpenAI Team Update 1 comment

    • They have plenty of results. All their work on GANs[1][2] has been great, and the OpenAI gym has proven to be pretty popular for reinforcement learning research already. I'm not sure how "hype" is measured - perhaps people thought they were going to invent some kind of AI entity…

      nlView on HNParent context

  6. Generative Models 1 comment

    • Brief summary: a nice intro about what generative models are and the current popular approaches/papers, followed by descriptions of recent work by OpenAI in the space. Quick links to papers mentioned: Improving GANs https://arxiv.org/abs/1606.03498 Improving VAEs…

      andreykView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.