推荐系统/计算广告相关资料整理

1.学习之路

1.1.基础阶段

参考资料：[1]《推荐系统实践》，项亮；[2]《推荐系统开发实战》，高阳团；[3]《美团机器学习实践》，美团算法团队；[4]《计算广告》，刘鹏。注意：[3]和[4]更多的偏重概念，代码不多。

1.2.进阶之路

主要参考知乎回答：想学习推荐系统，如何从小白成为高手?第一个回答者"刘十三"，整理的资料很不错，嘿嘿嘿~

1.2.1.推荐系统/计算广告/机器学习/CTR预估资料汇总

github链接：https://github.com/AllenZqy/RecSys

1.2.2.推荐/搜索/广告 精选文章

github链接：https://github.com/AllenZqy/RecNews

1.2.3.经典论文

作者：石晓文
链接：https://www.zhihu.com/question/23194692/answer/805896718
来源：知乎
著作权归作者所有。商业转载请联系作者获得授权，非商业转载请注明出处。

FM：《Factorization Machines》
FFM：《Field-aware Factorization Machines for CTR Prediction》
DeepFM：《DeepFM: A Factorization-Machine based Neural Network for CTR Prediction》Wide & Deep：《Wide & Deep Learning for Recommender Systems》
DCN：《Deep & Cross Network for Ad Click Predictions》
NFM：《Neural Factorization Machines for Sparse Predictive Analytics》
AFM：《Attentional Factorization Machines:Learning the Weight of Feature Interactions via Attention Networks》
GBDT + LR：《Practical Lessons from Predicting Clicks on Ads at Facebook》
MLR：《Learning Piece-wise Linear Modelsfrom Large Scale Data for Ad Click Prediction》
DIN：《Deep Interest Network for Click-Through Rate Prediction》
DIEN：《Deep Interest Evolution Network for Click-Through Rate Prediction》
BPR：《BPR: Bayesian Personalized Ranking from Implicit Feedback》
Youtube：《Deep Neural Networks for YouTube Recommendations》

1.2.4.持续跟进最新论文

作者：石晓文
链接：https://www.zhihu.com/question/23194692/answer/805896718
来源：知乎
著作权归作者所有。商业转载请联系作者获得授权，非商业转载请注明出处。

在不断跟进推荐系统论文的过程中，你会发现推荐系统会借鉴各个领域的方法， 持续跟进最近推荐论文，对我们学习其他领域如NLP、图像领域、强化学习等等都会有所帮助。接下来列举一些借鉴其他领域方法的一些文章吧，也算是对第三部分的一个补充。
强化学习
[1]《DRN: A Deep Reinforcement Learning Framework for News Recommendation》
[2]《Deep Reinforcement Learning for List-wise Recommendations》
多任务学习
[1]《Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate》
[2]《Why I like it: Multi-task Learning for Recommendation and Explanation》
GAN
[1]《IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models》
[2]《CFGAN: A Generic Collaborative Filtering Framework based on Generative Adversarial Networks》
知识图谱
[1]《DKN: Deep Knowledge-Aware Network for News Recommendation》
[2]《RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems》
[3]《Multi-task Learning for KG enhanced Recommendation》
[4]《Perceive Your Users in Depth: Learning Universal User Representations from Multiple E-commerce Tasks》
Transformer
[1]《Next Item Recommendation with Self-Attention》
[2]《Deep Session Interest Network for Click-Through Rate Prediction》
[3]《Behavior Sequence Transformer for E-commerce Recommendation in Alibaba》
[4]《BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer》
RNN & GNN
[1]《SESSION-BASED RECOMMENDATIONS WITH RECURRENT NEURAL NETWORKS》
[2]《Improved Recurrent Neural Networks for Session-based Recommendations》
[3]《Session-based Recommendation with Graph Neural Networks》
Embedding技巧
[1]《Real-time Personalization using Embeddings for Search Ranking at Airbnb》
[2]《Learning and Transferring IDs Representation in E-commerce》
[3]《Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba》