{
  "id": "1807.01202",
  "version": "v1",
  "published": "2018-07-03T14:26:57.000Z",
  "updated": "2018-07-03T14:26:57.000Z",
  "title": "Generating Multi-Categorical Samples with Generative Adversarial Networks",
  "authors": [
    "Ramiro Camino",
    "Christian Hammerschmidt",
    "Radu State"
  ],
  "journal": "Presented at the ICML 2018 workshop on Theoretical Foundations and Applications of Deep Generative Models, Stockholm, Sweden, PMLR 80, 2018",
  "categories": [
    "stat.ML",
    "cs.LG"
  ],
  "abstract": "We propose a method to train generative adversarial networks on mutivariate feature vectors representing multiple categorical values. In contrast to the continuous domain, where GAN-based methods have delivered considerable results, GANs struggle to perform equally well on discrete data. We propose and compare several architectures based on multiple (Gumbel) softmax output layers taking into account the structure of the data. We evaluate the performance of our architecture on datasets with different sparsity, number of features, ranges of categorical values, and dependencies among the features. Our proposed architecture and method outperforms existing models.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-07-03T14:26:57.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "generative adversarial networks",
      "generating multi-categorical samples",
      "representing multiple categorical values",
      "vectors representing multiple categorical",
      "mutivariate feature vectors representing multiple"
    ],
    "tags": [
      "journal article"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}