涨指标的方法02：召回
这节课的内容是推荐系统涨指标的方法。具体讲解如何通过改进召回模型（retrieval models）来提升推荐系统的核心指标。这节课的内容分三部分：双塔模型、Item-to-Item (I2I)、还有小众的召回模型（比如PDN、Deep Retrieval、SINE、M2GRL）。
参考文献
[1] Li et al. Path-based Deep Network for Candidate Item Matching in Recommenders. In SIGIR, 2021.
[2] Gao et al. Learning an end-to-end structure for retrieval in large-scale recommendations. In CIKM, 2021.
[3] Tan et al. Sparse-interest network for sequential recommendation. In WSDM, 2021.
[4] Wang et al. M2GRL: A multitask multi-view graph representation learning framework for web-scale recommender systems. In KDD, 2020.
课件链接： https://github.com/wangshusen/Recomme...
参考文献：https://arxiv.org/abs/2308.01204