{"ID":2887086,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.05673","arxiv_id":"2508.05673","title":"Breaking the Top-$K$ Barrier: Advancing Top-$K$ Ranking Metrics Optimization in Recommender Systems","abstract":"In the realm of recommender systems (RS), Top-$K$ ranking metrics such as NDCG@$K$ are the gold standard for evaluating recommendation performance. However, during the training of recommendation models, optimizing NDCG@$K$ poses significant challenges due to its inherent discontinuous nature and the intricate Top-$K$ truncation. Recent efforts to optimize NDCG@$K$ have either overlooked the Top-$K$ truncation or suffered from high computational costs and training instability. To overcome these limitations, we propose SoftmaxLoss@$K$ (SL@$K$), a novel recommendation loss tailored for NDCG@$K$ optimization. Specifically, we integrate the quantile technique to handle Top-$K$ truncation and derive a smooth upper bound for optimizing NDCG@$K$ to address discontinuity. The resulting SL@$K$ loss has several desirable properties, including theoretical guarantees, ease of implementation, computational efficiency, gradient stability, and noise robustness. Extensive experiments on four real-world datasets and three recommendation backbones demonstrate that SL@$K$ outperforms existing losses with a notable average improvement of 6.03%. The code is available at https://github.com/Tiny-Snow/IR-Benchmark.","short_abstract":"In the realm of recommender systems (RS), Top-$K$ ranking metrics such as NDCG@$K$ are the gold standard for evaluating recommendation performance. However, during the training of recommendation models, optimizing NDCG@$K$ poses significant challenges due to its inherent discontinuous nature and the intricate Top-$K$ t...","url_abs":"https://arxiv.org/abs/2508.05673","url_pdf":"https://arxiv.org/pdf/2508.05673v1","authors":"[\"Weiqin Yang\",\"Jiawei Chen\",\"Shengjia Zhang\",\"Peng Wu\",\"Yuegang Sun\",\"Yan Feng\",\"Chun Chen\",\"Can Wang\"]","published":"2025-08-04T17:50:02Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.AI\",\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":611392,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2887086,"paper_url":"https://arxiv.org/abs/2508.05673","paper_title":"Breaking the Top-$K$ Barrier: Advancing Top-$K$ Ranking Metrics Optimization in Recommender Systems","repo_url":"https://github.com/Tiny-Snow/IR-Benchmark","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}