发表机构
University of Electronic Science and Technology of China; Macau Polytechnic University; University of Liverpool（电子科技大学; 澳门理工大学; 利物浦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对PCVR预测中特征结构不匹配问题，提出RoleMix统一交互架构，通过语义令牌化表示顺序和非顺序证据，经两阶段处理和联合细化用于预测，在KDD Cup 2026挑战赛中表现出色，凸显保留字段语义的重要性。
AI 中文摘要
点击后转化率（PCVR）预测是工业推荐的核心，但稀疏、无序的多字段特征与长的、特定领域的行为历史之间的结构不匹配仍带来挑战。现有模型常通过单独路径处理信号并在后期融合，削弱了语义角色并限制了跨信号细化。我们提出RoleMix，一种统一交互架构，通过共享的、保留角色的令牌接口表示顺序和非顺序证据。非顺序字段转换为明确语义令牌，长行为域通过两阶段分层窗口注意力压缩为项目和上下文感知序列查询令牌。最终的全局、语义和序列查询令牌由堆叠的UniMixing-Lite块联合细化用于PCVR预测。在大规模KDD Cup 2026腾讯UniRec挑战赛中，RoleMix实现了83.648%的在线AUC，比官方工业基线高出1.953%。消融研究表明语义令牌化带来最大的孤立增益，突出了大规模PCVR建模的关键原则：在令牌接口级别保留字段语义与扩展交互主干同样重要。
英文摘要
Post-click conversion rate (PCVR) prediction is central to industrial recommendation, but remains challenged by the structural mismatch between sparse, unordered multi-field features and long, domain-specific behavior histories. Existing models often process these signals through separate pathways and fuse them late, weakening semantic roles and limiting cross-signal refinement. We propose RoleMix, a unified interaction architecture that represents sequential and non-sequential evidence through a shared, role-preserving token interface. Non-sequential fields are converted into explicit semantic tokens that preserve user, item, pairwise, dense, contextual, and cross-feature roles, while long behavior domains are compressed into item- and context-aware sequence-query tokens through two-stage hierarchical window attention. The resulting global, semantic, and sequence-query tokens are jointly refined by stacked UniMixing-Lite blocks for PCVR prediction. On the large-scale KDD Cup 2026 Tencent UniRec Challenge, RoleMix achieves 83.648% online AUC, outperforming the official industrial baseline by 1.953%. Ablation studies show that semantic tokenization yields the largest isolated gain, highlighting a key principle for large-scale PCVR modeling: preserving field semantics at the token-interface level is as important as scaling the interaction backbone.
CommentsKDD Cup 2026 Tencent UniRec Challenge
