/Recommender-System-Pytorch

基于 Pytorch 实现推荐系统相关的算法

Primary LanguageJupyter Notebook

Recommender System Pytorch

基于 Pytorch 实现推荐系统相关的算法。

想着看过书和论文后，能自己实现一下加深理解。

  • 模型在 notebook 文件中都有实现效果；
  • 其中关于 Embedding 部分的思路及代码参考自 pytorch-fm；

Datasets

  • MovieLens：ml-latest-small 中的 ratings.csv，共 1m 条记录；
  • Criteo：截取头部 100k 条；
  • Amazon Books：已经处理好的数据来源于 DIEN-pipeline，截取头部 100k 条；

Data Processing

数据处理方法参考自 Recommender-System-with-TF2.0：

  • 连续型数据：分箱后进行 One-hot 编码。
  • 类别型数据：One-hot 编码。

Available Models

Model Paper
Logistic Regression, LR
Mixed Logistic Regression, MLR Kun Gai, et al. Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction, 2017.
GBDT + LR
Factorization Machine, FM S Rendle, Factorization Machines, 2010.
Field-aware Factorization Machine, FFM Y Juan, et al. Field-aware Factorization Machines for CTR Prediction, 2015.
Deep Crossing Ying Shan, et al.Deep Crossing: Web-Scale Modeling without Manually Crafted Combinatorial Features, 2016.
Product-based Neural Network, PNN Y Qu, et al. Product-based Neural Networks for User Response Prediction, 2016.
Wide & Deep HT Cheng, et al. Wide & Deep Learning for Recommender Systems, 2016.
Deep & Cross Network, DCN R Wang, et al. Deep & Cross Network for Ad Click Predictions, 2017.
Factorization Machine supported Neural Network, FNN W Zhang, et al. Deep Learning over Multi-field Categorical Data - A Case Study on User Response Prediction, 2016.
DeepFM H Guo, et al. DeepFM: A Factorization-Machine based Neural Network for CTR Prediction, 2017.
Neural Factorization Machine, NFM X He and TS Chua, Neural Factorization Machines for Sparse Predictive Analytics, 2017.
Attentional Factorization Machine, AFM J Xiao, et al. Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks, 2017.
Deep Interest Network, DIN Guorui Zhou, et al. Deep Interest Network for Click-Through Rate Prediction, 2017.
Deep Interest Evolution Network, DIEN Guorui Zhou, et al. Deep Interest Evolution Network for Click-Through Rate Prediction, 2018.
Latent Factor Model, LFM
Neural Collaborative Filtering, NeuralCF X He, et al. Neural Collaborative Filtering, 2017.