LIFT：面向统一检索与排序的生命周期感知交互分解 Transformer
原标题：LIFT: A Lifecycle-aware Interaction Factorization Transformer for Unified Retrieval and Ranking
AI 摘要
论文提出 LIFT（Lifecycle-aware Interaction Factorization Transformer），将每次交互分解为 Request、Item、Context、Action 四个有序状态并建模为因果序列，检索读取 Request 状态、排序读取 Context 状态，从而在共享历史建模的同时保留各阶段特有信息。方法采用 Role-Conditioned Attention 和轻量 Pre-LN Bias 实现，在 ML-20M 和 Taobao 数据集上取得最高 Joint Score，分别比最强基线提升 4.9% 和 3.6%。
正文节选
LIFT: A Lifecycle-aware Interaction Factorization Transformer for Unified Retrieval and Ranking Abstract Cascaded recommender systems use the same user history for retrieval and ranking, while the two stages have access to different information at different points of an interaction. We propose the Lifecycle-aware Interaction Factorization Transformer (LIFT), which decomposes each interaction into ordered Request, Item, Context, and Action states and models them as a causal sequence. Retrieval