{
  "id": "2408.03977",
  "version": "v1",
  "published": "2024-08-07T14:15:18.000Z",
  "updated": "2024-08-07T14:15:18.000Z",
  "title": "Learning from Noisy Labels for Long-tailed Data via Optimal Transport",
  "authors": [
    "Mengting Li",
    "Chuang Zhu"
  ],
  "categories": [
    "cs.LG",
    "cs.AI"
  ],
  "abstract": "Noisy labels, which are common in real-world datasets, can significantly impair the training of deep learning models. However, recent adversarial noise-combating methods overlook the long-tailed distribution of real data, which can significantly harm the effect of denoising strategies. Meanwhile, the mismanagement of noisy labels further compromises the model's ability to handle long-tailed data. To tackle this issue, we propose a novel approach to manage data characterized by both long-tailed distributions and noisy labels. First, we introduce a loss-distance cross-selection module, which integrates class predictions and feature distributions to filter clean samples, effectively addressing uncertainties introduced by noisy labels and long-tailed distributions. Subsequently, we employ optimal transport strategies to generate pseudo-labels for the noise set in a semi-supervised training manner, enhancing pseudo-label quality while mitigating the effects of sample scarcity caused by the long-tailed distribution. We conduct experiments on both synthetic and real-world datasets, and the comprehensive experimental results demonstrate that our method surpasses current state-of-the-art methods. Our code will be available in the future.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2024-08-07T14:15:18.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "noisy labels",
      "long-tailed data",
      "long-tailed distribution",
      "method surpasses current state-of-the-art methods",
      "real-world datasets"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}