POEM: Partial-Order Enhanced Real-Time Sequential Modeling for Recommendation
2026-06-29 • Information Retrieval
Information Retrieval
AI summaryⓘ
The authors address the problem that real-time recommendation systems often miss quick changes in what users like and ignore helpful signals from earlier ranking steps. They propose POEM, which uses rankings from previous steps to build a flexible sequence of user interests based on partial orders rather than just time order. Their method combines different ranking scores into one representation and trains the model using user feedback and challenging examples. When tested on Kuaishou's platform, POEM improved average watch time slightly but consistently.
real-time recommendationsequential modelingpartial-orderranking scoresclick-through rate (CTR)multi-task learningpairwise lossuser interest modelingranking pipelinepositive and negative sampling
Authors
Linxiao Che, Yijia Sun, Siyuan Lou, Shanshan Huang, Qiang Luo, Ruiming Tang, Han Li, Kun Gai
Abstract
Real-time recommendation systems suffer from the dynamic drift of user interests and varying contextual conditions. Conventional sequential recommendation models only exploit static historical click sequences, which fail to capture instant preference changes and overlook structured signals hidden within the multi-stage ranking pipeline of industrial recommendation systems. To tackle these limitations, we propose POEM (Partial-Order Enhanced Modeling), a new real-time sequential modeling framework built upon intrinsic partial-order relations from the recommendation cascade. POEM takes real-time multi-task ranking scores (including predicted CTR and predicted watch duration) generated by upstream ranking modules as supervision to construct dynamic partial-order sequences, supporting fine-grained real-time interest modeling and consistent optimization between system ranking targets and user behavioral patterns. We summarize our core contributions as three aspects: (1) a partial-order guided sequence construction paradigm, which enriches vanilla chronological sequences via dynamic grouping and sampling conditioned on real-time ranking scores to reassess user interests per request; (2) a multi-objective score fusion module that unifies heterogeneous ranking signals into a compact quintuple representation with normalized rank-aware weighting; (3) a hierarchical sample learning strategy, which adopts system-favored high-ranked items and user positive feedback (e.g., long-duration watched videos) as positive instances, paired with graph-mined hard negatives and a margin-based pairwise loss for robust training. Fully deployed on Kuaishou online traffic, POEM achieves significant online gains: average per-user watch time lifts by 0.249% on the KS Single Page and 0.213% on the KS Lite Page.