提出新损失函数，让推荐系统在优化排名指标时更准更快。
Breaking the Top-$K$ Barrier: Advancing Top-$K$ Ranking Metrics Optimization in Recommender Systems
- 用分位数处理截断，构造平滑上界解决不连续问题
- 在四个数据集上平均提升6.03%，优于现有方法
- 适合关注精准排名的推荐系统研究者
在推荐系统中，NDCG@$K$ 是评估推荐性能的黄金标准。然而，训练过程中直接优化 NDCG@$K$ 因其固有的不连续性及复杂的 Top-$K$ 截断而面临挑战。近期方法或忽略截断问题，或存在计算成本高、训练不稳定等缺陷。为此，本文提出 SoftmaxLoss@$K$（SL@$K$），一种专为 NDCG@$K$ 优化设计的新损失函数。通过引入分位数技术处理 Top-$K$ 截断，并推导出可优化的平滑上界以应对不连续性。所提 SL@$K$ 具有理论保证、实现简单、计算高效、梯度稳定和抗噪性强等优点。在四个真实世界数据集与三种推荐模型上的大量实验表明，SL@$K$ 平均性能提升 6.03%。代码已开源：https://github.com/Tiny-Snow/IR-Benchmark。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。