{
  "id": "1806.03316",
  "version": "v1",
  "published": "2018-06-08T18:42:14.000Z",
  "updated": "2018-06-08T18:42:14.000Z",
  "title": "Adversarial Meta-Learning",
  "authors": [
    "Chengxiang Yin",
    "Jian Tang",
    "Zhiyuan Xu",
    "Yanzhi Wang"
  ],
  "comment": "10 pages, this paper was submitted to NIPS 2018",
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "Meta-learning enables a model to learn from very limited data to undertake a new task. In this paper, we study the general meta-learning with adversarial samples. We present a meta-learning algorithm, ADML (ADversarial Meta-Learner), which leverages clean and adversarial samples to optimize the initialization of a learning model in an adversarial manner. ADML leads to the following desirable properties: 1) it turns out to be very effective even in the cases with only clean samples; 2) it is model-agnostic, i.e., it is compatible with any learning model that can be trained with gradient descent; and most importantly, 3) it is robust to adversarial samples, i.e., unlike other meta-learning methods, it only leads to a minor performance degradation when there are adversarial samples. We show via extensive experiments that ADML delivers the state-of-the-art performance on two widely-used image datasets, MiniImageNet and CIFAR100, in terms of both accuracy and robustness.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-06-08T18:42:14.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "adversarial samples",
      "adversarial meta-learning",
      "learning model",
      "minor performance degradation",
      "adversarial meta-learner"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 10,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}