针对点击后转化率预测，提出结构化分词与目标感知兴趣表示框架
STAR: Structured Tokenization and Target-Aware Interest Representation for PCVR Prediction
- 用结构化分词和目标感知编码建模用户多行为序列
- 在挑战数据集上提升排序AUC，LogLoss显示校准良好
- 适合工业级推荐系统，尤其处理高基数稀疏特征场景
点击后转化率（PCVR）预测是工业推荐系统中的核心排序任务。现代排序模型需同时捕捉异构非序列特征、多行为用户序列及目标物品感知的用户兴趣，同时对高基数稀疏特征、缺失值和训练推理不一致保持鲁棒性。本文提出STAR（结构化分词与目标感知兴趣表示），作为KDD Cup 2026腾讯UniRec挑战赛的实用框架。STAR基于HyFormer风格的多序列骨干网络，结合结构化特征分词与目标感知兴趣表示，引入高基数信号恢复、显式用户-物品交互标记、目标感知序列解码，以及受InfoNCE启发的加权用户-物品对比辅助目标。通过从保存的训练配置中重建特征映射表和结构超参数，进一步对齐训练与推理流程。在挑战数据集上的实验识别出显著提升排序AUC的关键组件，同时报告了LogLoss作为校准诊断。主要消融研究显示时间上下文带来大幅增益，对比对齐、目标感知兴趣编码及高基数序列特征恢复也有小但有益的贡献。
原文摘要 · Abstract (English)
Post-click conversion rate (PCVR) prediction is a core ranking task in industrial recommender systems. Modern ranking models must jointly capture heterogeneous non-sequential features, multi-behavior user sequences, and target-item-aware user interests, while remaining robust to high-cardinality sparse features, missing values, and train-inference inconsistencies. In this paper, we present STAR (Structured Tokenization and Target-Aware Interest Representation), a practical framework for the KDD Cup 2026 Tencent UniRec Challenge. STAR combines structured feature tokenization with target-aware interest representation on top of a HyFormer-style multi-sequence backbone. It introduces high-cardinality signal recovery, explicit user-item interaction tokens, target-aware sequence decoding, and a weighted user-item contrastive auxiliary objective inspired by InfoNCE. We further align the training and inference pipelines by reconstructing feature remapping tables and structural hyperparameters from the saved training configuration. Experiments on the challenge dataset identify the components that most reliably improve ranking AUC, while LogLoss is reported as a calibration diagnostic. The main ablation study shows a large gain from temporal context, with smaller but useful contributions from contrastive alignment, target-aware interest encoding, and high-cardinality sequence feature recovery.
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。