{
  "id": "2101.11201",
  "version": "v1",
  "published": "2021-01-27T04:37:34.000Z",
  "updated": "2021-01-27T04:37:34.000Z",
  "title": "Similarity of Classification Tasks",
  "authors": [
    "Cuong Nguyen",
    "Thanh-Toan Do",
    "Gustavo Carneiro"
  ],
  "comment": "Accepted at Neurips Meta-learning Workshop 2020",
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "Recent advances in meta-learning has led to remarkable performances on several few-shot learning benchmarks. However, such success often ignores the similarity between training and testing tasks, resulting in a potential bias evaluation. We, therefore, propose a generative approach based on a variant of Latent Dirichlet Allocation to analyse task similarity to optimise and better understand the performance of meta-learning. We demonstrate that the proposed method can provide an insightful evaluation for meta-learning algorithms on two few-shot classification benchmarks that matches common intuition: the more similar the higher performance. Based on this similarity measure, we propose a task-selection strategy for meta-learning and show that it can produce more accurate classification results than methods that randomly select training tasks.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2021-01-27T04:37:34.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "classification tasks",
      "analyse task similarity",
      "latent dirichlet allocation",
      "potential bias evaluation",
      "performance"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}