{
  "id": "2403.02683",
  "version": "v1",
  "published": "2024-03-05T06:10:28.000Z",
  "updated": "2024-03-05T06:10:28.000Z",
  "title": "Learning to Defer to a Population: A Meta-Learning Approach",
  "authors": [
    "Dharmesh Tailor",
    "Aditya Patra",
    "Rajeev Verma",
    "Putra Manggala",
    "Eric Nalisnick"
  ],
  "comment": "Accepted at the 27th International Conference on Artificial Intelligence and Statistics (AISTATS 2024)",
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "The learning to defer (L2D) framework allows autonomous systems to be safe and robust by allocating difficult decisions to a human expert. All existing work on L2D assumes that each expert is well-identified, and if any expert were to change, the system should be re-trained. In this work, we alleviate this constraint, formulating an L2D system that can cope with never-before-seen experts at test-time. We accomplish this by using meta-learning, considering both optimization- and model-based variants. Given a small context set to characterize the currently available expert, our framework can quickly adapt its deferral policy. For the model-based approach, we employ an attention mechanism that is able to look for points in the context set that are similar to a given test point, leading to an even more precise assessment of the expert's abilities. In the experiments, we validate our methods on image recognition, traffic sign detection, and skin lesion diagnosis benchmarks.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2024-03-05T06:10:28.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "meta-learning approach",
      "skin lesion diagnosis benchmarks",
      "population",
      "traffic sign detection",
      "small context set"
    ],
    "tags": [
      "conference paper"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}