候选依赖残差路由在序列推荐中以顶部精度换召回
原标题：Candidate-dependent residual routing trades top-of-list accuracy for recall in sequential recommendation
AI 摘要
研究者在一个基于SASRec的自注意力序列推荐基线之上，加入一个小型残差路由模块，并对比两种版本：路由权重由用户历史表示决定（用户依赖）或由候选物品嵌入决定（候选依赖）。在REES46化妆品商店数据集上用五个配对随机种子做全目录评估，候选依赖路由对NDCG@10几乎无影响（平均相对变化+0.003%），但召回率提升1.81%，而首个相关物品的平均倒数排名下降，新增命中多落在第6至第10位。增益来自用户最近50个事件中至少含一个目标的查询，目标全在该窗口之外的查询反而变差，说明该路由以牺牲列表顶部精度换取更靠后的召回。
正文节选
Candidate-dependent residual routing trades top-of-list accuracy for recall in sequential recommendation Abstract Candidate-dependent routing lets a sequential recommender weight a user’s past behaviors differently for each item it scores. We test whether this flexibility helps by adding a small residual routing module to a self-attentive baseline, in two versions that differ only in what sets the routing weights: the user’s history representation or the candidate item’s embedding. Across five p