优化推荐系统的层级标识符，大幅提升训练速度且保持推荐质量。
Efficient Optimization of Hierarchical Identifiers for Generative Recommendation
- 用平衡树结构构建物品标识符，结合对比学习提升检索效率。
- 新方法将树构建时间压缩至原方法的2%~8%，大集合下仍保持高精度。
- 适合关注大规模推荐系统高效训练的工程师与研究者。
SEATER 是一种生成式检索模型，通过使用平衡树结构的物品标识符和对比学习目标，提升了推荐推理效率与检索质量。我们在原始论文的所有数据集上复现并验证了 SEATER 在检索质量上的优势，并将其评估扩展至 Yambda——一个大规模音乐推荐数据集。实验验证了 SEATER 的强性能，但发现其训练中的树构建步骤在物品数量增加时成为主要瓶颈。为此，我们实现并评估了两种替代构建算法：一种贪心法以最小化构建时间为目标，另一种混合方法在高层采用贪心聚类、低层采用更精确分组。贪心法将树构建时间降低至原方法的2%以下，仅在最大数据集上略有质量下降；混合法在保持原版质量的基础上，甚至在最大数据集上表现更优，同时将构建时间压缩至5%-8%。所有数据与代码均已公开，确保完全可复现（https://github.com/joshrosie/re-seater）。
原文摘要 · Abstract (English)
SEATER is a generative retrieval model that improves recommendation inference efficiency and retrieval quality by utilizing balanced tree-structured item identifiers and contrastive training objectives. We reproduce and validate SEATER's reported improvements in retrieval quality over strong baselines across all datasets from the original work, and extend the evaluation to Yambda, a large-scale music recommendation dataset. Our experiments verify SEATER's strong performance, but show that its tree construction step during training becomes a major bottleneck as the number of items grows. To address this, we implement and evaluate two alternative construction algorithms: a greedy method optimized for minimal build time, and a hybrid method that combines greedy clustering at high levels with more precise grouping at lower levels. The greedy method reduces tree construction time to less than 2% of the original with only a minor drop in quality on the dataset with the largest item collection. The hybrid method achieves retrieval quality on par with the original, and even improves on the largest dataset, while cutting construction time to just 5-8%. All data and code are publicly available for full reproducibility at https://github.com/joshrosie/re-seater.
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。