MLGB是一个包含50+点击率预估和推荐系统深度模型（完整源码+说明）.zip

<p align="center"> <img src="https://github.com/UlionTse/mlgb/blob/main/docs/mlgb_logo.png" width="200"/> </p> <p align="center"> <a href="https://pypi.org/project/mlgb"><img alt="PyPI - Version" src="https://img.shields.io/pypi/v/mlgb.svg?color=blue"></a> <a href="https://anaconda.org/conda-forge/mlgb"><img alt="Conda - Version" src="https://img.shields.io/conda/vn/conda-forge/mlgb.svg?color=blue"></a> <a href="https://pypi.org/project/mlgb"><img alt="PyPI - License" src="https://img.shields.io/pypi/l/mlgb.svg?color=brightgreen"></a> <a href="https://pypi.org/project/mlgb"><img alt="PyPI - Python" src="https://img.shields.io/pypi/pyversions/mlgb.svg?color=blue"></a> <a href="https://pypi.org/project/mlgb"><img alt="PyPI - Status" src="https://img.shields.io/pypi/status/mlgb.svg?color=brightgreen"></a> <a href="https://pypi.org/project/mlgb"><img alt="PyPI - Wheel" src="https://img.shields.io/badge/wheel-yes-brightgreen.svg"></a> <a href="https://pypi.org/project/mlgb"><img alt="PyPI - Downloads" src="https://static.pepy.tech/personalized-badge/mlgb?period=total&units=international_system&left_text=downloads&left_color=grey&right_color=blue"></a> <a href="https://pypi.org/project/mlgb"><img alt="PyPI - TensorFlow" src="https://img.shields.io/badge/TensorFlow-2.10+-yellow.svg"></a> <a href="https://pypi.org/project/mlgb"><img alt="PyPI - PyTorch" src="https://img.shields.io/badge/PyTorch-2.1+-tomato.svg"></a> </p> * * * **MLGB** means **M**achine **L**earning of the **G**reat **B**oss, and is called **「妙计包」**. **MLGB** is a library that includes many models of CTR Prediction & Recommender System by TensorFlow & PyTorch. - [Advantages](#advantages) - [Supported Models](#supported-models) - [Installation](#installation) - [Getting Started](#getting-started) - [Code Examples](#code-examples) - [Citation](#citation) ## Advantages - **Easy!** Use `mlgb.get_model(model_name, **kwargs)` to get a complex model. - **Fast!** Better performance through better code. - **Enjoyable!** 50+ ranking & matching models to use, 2 languages(TensorFlow & PyTorch) to deploy. ## Supported Models | ID | Model Name | Paper Link | Paper Team | Paper Year | | --- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------- | ---------- | | <tr><th colspan=5 align="center">:open_file_folder: **Ranking-Model::Normal** :point_down:</th></tr> | | 1 | LR | [Predicting Clicks: Estimating the Click-Through Rate for New Ads](https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/predictingclicks.pdf) | Microsoft | 2007 | | 2 | PLM/MLR | [Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction](https://arxiv.org/pdf/1704.05194.pdf) | Alibaba | 2017 | | 3 | MLP/DNN | [Neural Networks for Pattern Recognition](http://diyhpl.us/~bryan/papers2/ai/ahuman-pdf-only/neural-networks/2005-Pattern%20Recognition.pdf) | Christopher M. Bishop(Microsoft, 1997-Present), Foreword by Geoffrey Hinton. | 1995 | | 4 | DLRM | [Deep Learning Recommendation Model for Personalization and Recommendation Systems](https://arxiv.org/pdf/1906.00091.pdf) | Facebook(Meta) | 2019 | | 5 | MaskNet | [MaskNet: Introducing Feature-Wise Multiplication to CTR Ranking Models by Instance-Guided Mask](https://arxiv.org/pdf/2102.07619.pdf) | Weibo(Sina) | 2021 | | | | | | | | 6 | DCM/DeepCross | [Deep Crossing: Web-Scale Modeling without Manually Crafted Combinatorial Features](https://www.kdd.org/kdd2016/papers/files/adf0975-shanA.pdf) | Microsoft | 2016 | | 7 | DCN | [DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems](https://arxiv.org/pdf/2008.13535.pdf), [v1](https://arxiv.org/pdf/1708.05123.pdf) | Google(Alphabet) | 2017, 2020 | | 8 | EDCN | [Enhancing Explicit and Implicit Feature Interactions via Information Sharing for Parallel Deep CTR Models](https://dlp-kdd.github.io/assets/pdf/DLP-KDD_2021_paper_12.pdf) | Huawei | 2021 | | | | | | | | 9 | FM | [Factorization Machines](https://cseweb.ucsd.edu/classes/fa17/cse291-b/reading/Rendle2010FM.pdf) | Steffen Rendle(Google, 2013-Present) | 2010 | | 10 | FFM | [Field-aware Factorization Machines for CTR Prediction](https://www.csie.ntu.edu.tw/~cjlin/papers/ffm.pdf) | NTU | 2016 | | 11 | HOFM | [Higher-Order Factorization Machines](https://arxiv.org/pdf/1607.07195v2.pdf) | NTT | 2016 | | 12 | FwFM | [Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising](https://arxiv.org/pdf/1806.03514.pdf) | Junwei Pan(Yahoo), etc. | 2018, 2020 | | 13 | FmFM | [FM^2: Field-matrixed Factorization Machines for Recommender Systems](https://arxiv.org/pdf/2102.12994v2.pdf) | Yahoo | 2021 | | 14 | FEFM | [FIELD-EMBEDDED FACTORIZATION MACHINES FOR CLICK-THROUGH RATE PREDICTION](https://arxiv.org/pdf/2009.09931v2.pdf) | Harshit Pande(Adobe) | 2020, 2021 | | 15 | AFM | [Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks](https://arxiv.org/pdf/1708.04617.pdf) | ZJU&NUS(Jun Xiao(ZJU), Xiangnan He(NUS), etc.) | 2017 | | 16 | LFM | [Learn