UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence
This work addresses the efficiency-effectiveness trade-off in modeling ultra-long user sequences for recommendation systems, offering a practical solution with measurable business impact.
UxSID introduces a semantic-group shared interest memory approach for ultra-long user sequence modeling, achieving state-of-the-art performance and a 0.337% revenue lift in a large-scale advertising A/B test.
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.