{
  "annotation_id": "e86f76dd-227e-4131-afd1-72897545e118",
  "date_created": "2026-02-17T05:53:23.797000Z",
  "date_modified": "2026-02-17T05:53:23.797000Z",
  "file_hash": "f2d3d314dd4d5c3b529ea51d4543ff28569d6f833d870dc89d6f23843d935679",
  "private": false,
  "record": {
    "abstract": "Content-based recommendation systems (CRSs) utilize content features to predict user-item interactions, serving as essential tools for helping users navigate information-rich web services. However, ensuring the effectiveness of CRSs requires large-scale and even continuous model training to accommodate diverse user preferences, resulting in significant computational costs and resource demands. A promising approach to this challenge is coreset selection, which identifies a small but representative subset of data samples that preserves model quality while reducing training overhead. Yet, the selected coreset is vulnerable to the pervasive noise in user-item interactions, particularly when it is minimally sized. To this end, we propose Noise-aware Coreset Selection (NaCS), a specialized framework for CRSs. NaCS constructs coresets through submodular optimization based on training gradients, while simultaneously correcting noisy labels using a progressively trained model. Meanwhile, we refine the selected coreset by filtering out low-confidence samples through uncertainty quantification, thereby avoid training with unreliable interactions. Through extensive experiments, we show that NaCS produces higher-quality coresets for CRSs while achieving better efficiency than existing coreset selection techniques. Notably, NaCS recovers 93-95\\% of full-dataset training performance using merely 1\\% of the training data. The source code is available at \\href{https://github.com/chenxing1999/nacs}{https://github.com/chenxing1999/nacs}.",
    "arxiv_id": "2601.10067",
    "authors": [
      "Hung Vinh Tran",
      "Tong Chen",
      "Hechuan Wen",
      "Quoc Viet Hung Nguyen",
      "Bin Cui",
      "Hongzhi Yin"
    ],
    "categories": [
      "cs.LG",
      "cs.IR"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Efficient Content-based Recommendation Model Training via Noise-aware Coreset Selection",
    "url": "https://arxiv.org/abs/2601.10067",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "0dd14a6f-4d9f-4643-97fd-c6deb84e786a",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}