{
  "id": "1809.01921",
  "version": "v1",
  "published": "2018-09-06T10:57:51.000Z",
  "updated": "2018-09-06T10:57:51.000Z",
  "title": "RDPD: Rich Data Helps Poor Data via Imitation",
  "authors": [
    "Shenda Hong",
    "Cao Xiao",
    "Tengfei Ma",
    "Hongyan Li",
    "Jimeng Sun"
  ],
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "In many situations, we have both rich- and poor- data environments: in a rich-data environment (e.g., intensive care units), we have high-quality multi-modality data. On the other hand, in a poor-data environment (e.g., at home), we often only have access to a single data modality with low quality. How can we learn an accurate and efficient model for the poor-data environment by leveraging multi-modality data from the rich-data environment? In this work, we propose a knowledge distillation model RDPD to enhance a small model trained on poor data with a complex model trained on rich data. In an end-to-end fashion, RDPD trains a student model built on a single modality data (poor data) to imitate the behavior and performance of a teacher model from multimodal data (rich data) via jointly optimizing the combined loss of attention imitation and target imitation. We evaluated RDPD on three real-world datasets. RDPD consistently outperformed all baselines across all three datasets, especially achieving the greatest performance improvement over a standard neural network model trained on the common features (Direct model) by 24.56% on PR-AUC and 12.21% on ROC-AUC, and over the standard knowledge distillation model by 5.91% on PR-AUC and 4.44% on ROC-AUC.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-09-06T10:57:51.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "rich data helps poor data",
      "environment",
      "standard neural network model",
      "standard knowledge distillation model",
      "knowledge distillation model rdpd"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}