用分层稀疏激活压缩用户长序列，提升推荐系统效率与精准度。
HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders
- 分层编码行为为语义ID，构建全局层级码本。
- 通过投票机制稀疏激活个性化兴趣代理，减少量化误差。
- 适合大规模推荐系统优化，尤其关注长尾偏好保留。
现代推荐系统利用超长用户行为序列捕捉动态偏好，但端到端建模在生产环境中因延迟和内存限制不可行。现有方法通过兴趣中心总结历史行为虽可行，却难以（1）在合适粒度上识别用户特定中心，（2）准确分配行为，导致量化误差并丢失长尾偏好。为此，我们提出分层稀疏激活压缩（HiSAC），一种高效的个性化序列建模框架。HiSAC将交互编码为多层级语义ID，构建全局层级码本；通过分层投票机制稀疏激活个性化兴趣代理作为细粒度偏好中心；基于这些代理，软路由注意力在语义空间聚合历史信号，按相似性加权以最小化量化误差并保留长尾行为。在淘宝“猜你喜欢”首页部署，HiSAC实现显著压缩与成本降低，线上A/B测试显示点击率持续提升1.65%，证明其可扩展性与实际有效性。
原文摘要 · Abstract (English)
Modern recommender systems leverage ultra-long user behavior sequences to capture dynamic preferences, but end-to-end modeling is infeasible in production due to latency and memory constraints. While summarizing history via interest centers offers a practical alternative, existing methods struggle to (1) identify user-specific centers at appropriate granularity and (2) accurately assign behaviors, leading to quantization errors and loss of long-tail preferences. To alleviate these issues, we propose Hierarchical Sparse Activation Compression (HiSAC), an efficient framework for personalized sequence modeling. HiSAC encodes interactions into multi-level semantic IDs and constructs a global hierarchical codebook. A hierarchical voting mechanism sparsely activates personalized interest-agents as fine-grained preference centers. Guided by these agents, Soft-Routing Attention aggregates historical signals in semantic space, weighting by similarity to minimize quantization error and retain long-tail behaviors. Deployed on Taobao's "Guess What You Like" homepage, HiSAC achieves significant compression and cost reduction, with online A/B tests showing a consistent 1.65% CTR uplift -- demonstrating its scalability and real-world effectiveness.
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。