MERGE：面向大规模流媒体推荐的下一代物品索引范式
MERGE: Next-Generation Item Indexing Paradigm for Large-Scale Streaming Recommendation
AI总结：
MERGE通过动态聚类和层次索引结构提升大规模流媒体推荐系统的物品索引效率和性能。
摘要：
物品索引，将大量物品映射为紧凑的离散表示，对于判别性和生成性推荐系统至关重要，但现有基于向量量化（VQ）的方法在流媒体行业推荐器中面临高度偏斜和非平稳的物品分布，导致分配精度低、聚类占用不平衡和聚类分离不足。为解决这些挑战，我们提出了MERGE，一种新一代的物品索引范式，能够从头开始构建聚类，动态监控聚类占用，并通过细到粗的合并形成层次索引结构。广泛实验表明，与现有索引方法相比，MERGE显著提高了分配精度、聚类均匀性和聚类分离度，而在线A/B测试显示在关键业务指标上取得了显著提升，凸显了其作为大规模推荐系统基础索引方法的潜力。
英文摘要：
Item indexing, which maps a large corpus of items into compact discrete representations, is critical for both discriminative and generative recommender systems, yet existing Vector Quantization (VQ)-based approaches struggle with the highly skewed and non-stationary item distributions common in industrial streaming recommenders, leading to poor assignment accuracy, imbalanced cluster occupancy, and insufficient cluster separation. To address these challenges, we propose MERGE, a next-generation item indexing paradigm that adaptively constructs clusters from scratch, dynamically monitors cluster occupancy, and forms hierarchical index structures via fine-to-coarse merging. Extensive experiments demonstrate that MERGE significantly improves assignment accuracy, cluster uniformity, and cluster separation compared with existing indexing methods, while online A/B tests show substantial gains in key business metrics, highlighting its potential as a foundational indexing approach for large-scale recommendation. Codes are available at https://github.com/baiyimeng/MERGE.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
