{
  "id": "1909.02180",
  "version": "v1",
  "published": "2019-09-05T01:55:35.000Z",
  "updated": "2019-09-05T01:55:35.000Z",
  "title": "Learning from Label Proportions with Generative Adversarial Networks",
  "authors": [
    "Jiabin Liu",
    "Bo Wang",
    "Zhiquan Qi",
    "Yingjie Tian",
    "Yong Shi"
  ],
  "comment": "Accepted as a conference paper at NeurIPS 2019. Work in progress",
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "In this paper, we leverage generative adversarial networks (GANs) to derive an effective algorithm LLP-GAN for learning from label proportions (LLP), where only the bag-level proportional information in labels is available. Endowed with end-to-end structure, LLP-GAN performs approximation in the light of an adversarial learning mechanism, without imposing restricted assumptions on distribution. Accordingly, we can directly induce the final instance-level classifier upon the discriminator. Under mild assumptions, we give the explicit generative representation and prove the global optimality for LLP-GAN. Additionally, compared with existing methods, our work empowers LLP solver with capable scalability inheriting from deep models. Several experiments on benchmark datasets demonstrate vivid advantages of the proposed approach.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-09-05T01:55:35.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "label proportions",
      "benchmark datasets demonstrate vivid advantages",
      "work empowers llp solver",
      "leverage generative adversarial networks",
      "bag-level proportional information"
    ],
    "tags": [
      "conference paper"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}