用离散标识符替代密集向量，实现推荐系统的高效存储与推理。
Tokens are All You Need: Dual-purpose Semantic IDs for Achieving LLM-Level I/O Efficiency in recommendation systems
- 将用户-物品交互嵌入压缩为可学习的离散语义标识符。
- 在线重建嵌入，减少存储开销，提升系统吞吐效率。
- 已在大规模视频平台落地，适合高并发推荐场景。
大规模推荐系统因海量密集嵌入表面临“内存墙”瓶颈。虽然生成式检索使用离散令牌表示ID，但高维上下文仍依赖低效的密集格式。受计算机视觉数据压缩启发，我们提出双用途语义标识符，实现类大模型级别的输入输出效率。方法采用分层量化，将连续嵌入压缩为离散语义标识符，同时承担两项功能：(1) 协同身份：通过可学习嵌入表建模用户-物品交互；(2) 内容重建：使用轻量级语义解码器实时近似重构嵌入。该方案以按需重建替代大规模向量存储，显著降低系统开销与数据足迹。我们在离线评估及某大型视频平台生产级排序与召回系统中成功部署，验证了离散令牌在内容丰富推荐中的高效性。
原文摘要 · Abstract (English)
Large-scale recommendation systems face "Memory Wall" bottlenecks due to massive, dense embedding tables. While generative retrieval uses discrete tokens for IDs, high-dimensional context still relies on inefficient dense formats. Inspired by computer vision data compression, we propose Dual-purpose Semantic IDs to achieve LLM-level I/O efficiency. Our methodology uses hierarchical quantization to condense continuous embeddings into discrete Semantic IDs performing two concurrent roles: (1) Collaborative Identity: modeling user-item interactions via learnable embedding table; and (2) Content Reconstruction: using a lightweight Semantic Decoder for on-the-fly embedding approximation. This approach replaces massive vector storage with on-demand reconstruction, reducing system overhead and data footprints. We demonstrate the efficacy of our framework through offline evaluations and successful online deployment in production-scale ranking and retrieval systems at a major video sharing platform, showing that discrete tokens are indeed all you need for highly efficient, content-rich recommendation.
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。