用语义分组记忆建模超长用户行为，兼顾效率与效果。
UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence
- 引入语义ID和双层注意力，共享兴趣记忆捕捉目标偏好。
- 在大规模广告测试中实现0.337%的收入提升，性能达领先水平。
- 适合需要高效处理超长序列推荐的工业场景使用。
建模超长用户序列面临效率与效果间的权衡难题。现有方法依赖项目特定搜索或项目无关压缩，我们提出UxSID框架，探索第三种路径：语义分组共享兴趣记忆。通过语义ID（SIDs）与双层注意力策略，UxSID在无需高成本项目特定模型的前提下，捕获目标感知偏好。该端到端架构兼具计算简洁性与语义感知能力，在大规模广告A/B测试中实现0.337%的收入提升，达到当前最优性能。
原文摘要 · Abstract (English)
Modeling ultra-long user sequences involves a difficult trade-off between efficiency and effectiveness. While current paradigms rely on either item-specific search or item-agnostic compression, we propose UxSID, a framework exploring a third path: semantic-group shared interest memory. By utilizing Semantic IDs (SIDs) and a dual-level attention strategy, UxSID captures target-aware preferences without the heavy cost of item-specific models. This end-to-end architecture balances computational parsimony with semantic awareness, achieving state-of-the-art performance and a 0.337% revenue lift in large-scale advertising A/B test.
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。