{
  "id": "1705.08395",
  "version": "v1",
  "published": "2017-05-23T16:27:19.000Z",
  "updated": "2017-05-23T16:27:19.000Z",
  "title": "Continual Learning in Generative Adversarial Nets",
  "authors": [
    "Ari Seff",
    "Alex Beatson",
    "Daniel Suo",
    "Han Liu"
  ],
  "categories": [
    "cs.LG",
    "cs.AI",
    "stat.ML"
  ],
  "abstract": "Developments in deep generative models have allowed for tractable learning of high-dimensional data distributions. While the employed learning procedures typically assume that training data is drawn i.i.d. from the distribution of interest, it may be desirable to model distinct distributions which are observed sequentially, such as when different classes are encountered over time. Although conditional variations of deep generative models permit multiple distributions to be modeled by a single network in a disentangled fashion, they are susceptible to catastrophic forgetting when the distributions are encountered sequentially. In this paper, we adapt recent work in reducing catastrophic forgetting to the task of training generative adversarial networks on a sequence of distinct distributions, enabling continual generative modeling.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2017-05-23T16:27:19.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "generative adversarial nets",
      "models permit multiple distributions",
      "learning procedures typically assume",
      "continual learning",
      "deep generative models permit multiple"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}