awesome-models

该仓库主要总结基于TensorFlow框架，实现的推荐模型。

TensorFlow基础部分：主要包括Tensorflow的基础op、变量初始化和激活函数的选择、常见loss及其应用、各种FeatureColumn的内部实现，以及底层EmbeddingLookup细节曝光。
模型部分：主要聚焦于推荐系统的特征交互、序列推荐、召回模型、多目标模型的结构和融合排序**。排序、召回等模块常用的模型结构均以Jupyter实现以探究不同模型算法在矩阵运算的具体细节。

Models List

Module	Model	Paper
特征交互	CAN	CAN: Feature Co-Action for Click-Through Rate Prediction
..	DCN	Deep & Cross Network for Ad Click Predictions
..	PNN	Product-based Neural Networks for User Response Prediction
..	AFM	Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks
..	DIN	Deep Interest Network for Click-Through Rate Prediction
..	FFM	Field-aware Factorization Machines for CTR Prediction
..	DeepFM	DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
..	DeepCrossing	Deep Crossing: Web-Scale Modeling without Manually Crafted Combinatorial Features
..	NCF	Neural Collaborative Filtering
..	NFM	Neural Factorization Machines for Sparse Predictive Analytics
多目标结构	MMoE	Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts
..	PLE	Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations
序列与召回	ComiRec	Controllable Multi-Interest Framework for Recommendation
..	STAMP	STAMP: Short-Term Attention/Memory Priority Model for Session-based Recommendation
..	SASRec	Self-Attentive Sequential Recommendation