提交 c167bf34 编写于 作者: W wuzhihua 提交者: tangwei

refine readme for rank and cu

上级 3865e855
......@@ -25,12 +25,12 @@
| TagSpace | 标签推荐 | [TagSpace: Semantic Embeddings from Hashtags (2014)](https://research.fb.com/publications/tagspace-semantic-embeddings-from-hashtags/) |
| Classification | 文本分类 | [Convolutional neural networks for sentence classication (2014)](https://www.aclweb.org/anthology/D14-1181.pdf) |
TagSpace模型
[TagSpace模型](https://research.fb.com/publications/tagspace-semantic-embeddings-from-hashtags)
<p align="center">
<img align="center" src="../../doc/imgs/tagspace.png">
<p>
文本分类CNN模型
[文本分类CNN模型](https://www.aclweb.org/anthology/D14-1181.pdf)
<p align="center">
<img align="center" src="../../doc/imgs/cnn-ckim2014.png">
<p>
......
# 排序模型库
## 简介
我们提供了常见的排序任务中使用的模型算法的PaddleRec实现, 单机训练&预测效果指标以及分布式训练&预测性能指标等。实现的排序模型包括 [多层神经网络](http://gitlab.baidu.com/tangwei12/paddlerec/tree/develop/models/rank/dnn)[Deep Cross Network](http://gitlab.baidu.com/tangwei12/paddlerec/tree/develop/models/rank/dcn)[DeepFM](http://gitlab.baidu.com/tangwei12/paddlerec/tree/develop/models/rank/deepfm)[xDeepFM](http://gitlab.baidu.com/tangwei12/paddlerec/tree/develop/models/rank/xdeepfm)[Deep Interest Network](http://gitlab.baidu.com/tangwei12/paddlerec/tree/develop/models/rank/din)[Wide&Deep](http://gitlab.baidu.com/tangwei12/paddlerec/tree/develop/models/rank/wide_deep)
我们提供了常见的排序任务中使用的模型算法的PaddleRec实现, 单机训练&预测效果指标以及分布式训练&预测性能指标等。实现的排序模型包括 [多层神经网络](dnn)[Deep Cross Network](dcn)[DeepFM](deepfm)[xDeepFM](xdeepfm)[Deep Interest Network](din)[Wide&Deep](wide_deep)
模型算法库在持续添加中,欢迎关注。
## 目录
* [整体介绍](#整体介绍)
* [排序模型列表](#排序模型列表)
* [模型列表](#模型列表)
* [使用教程](#使用教程)
* [数据处理](#数据处理)
* [训练](#训练)
......@@ -18,16 +18,41 @@
* [模型性能列表](#模型性能列表)
## 整体介绍
### 排序模型列表
### 模型列表
| 模型 | 简介 | 论文 |
| :------------------: | :--------------------: | :---------: |
| DNN | 多层神经网络 | -- |
| wide&deep | Deep + wide(LR) | [Wide & Deep Learning for Recommender Systems](https://dl.acm.org/doi/abs/10.1145/2988450.2988454)(2016) |
| DeepFM | DeepFM | [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://arxiv.org/abs/1703.04247)(2017) |
| xDeepFM | xDeepFM | [xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems](https://dl.acm.org/doi/abs/10.1145/3219819.3220023)(2018) |
| DCN | Deep Cross Network | [Deep & Cross Network for Ad Click Predictions](https://dl.acm.org/doi/abs/10.1145/3124749.3124754)(2017) |
| DIN | Deep Interest Network | [Deep Interest Network for Click-Through Rate Prediction](https://dl.acm.org/doi/abs/10.1145/3219819.3219823)(2018) |
| wide&deep | Deep + wide(LR) | [Wide & Deep Learning for Recommender Systems](https://dl.acm.org/doi/pdf/10.1145/2988450.2988454)(2016) |
| DeepFM | DeepFM | [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://arxiv.org/pdf/1703.04247.pdf)(2017) |
| DCN | Deep Cross Network | [Deep & Cross Network for Ad Click Predictions](https://dl.acm.org/doi/pdf/10.1145/3124749.3124754)(2017) |
| xDeepFM | xDeepFM | [xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems](https://dl.acm.org/doi/pdf/10.1145/3219819.3220023)(2018) |
| DIN | Deep Interest Network | [Deep Interest Network for Click-Through Rate Prediction](https://dl.acm.org/doi/pdf/10.1145/3219819.3219823)(2018) |
[wide&deep](https://dl.acm.org/doi/pdf/10.1145/2988450.2988454):
<p align="center">
<img align="center" src="../../doc/imgs/wide&deep.jpg">
<p>
[DeepFM](https://arxiv.org/pdf/1703.04247.pdf):
<p align="center">
<img align="center" src="../../doc/imgs/deepfm.jpg">
<p>
[XDeepFM](https://dl.acm.org/doi/pdf/10.1145/3219819.3220023):
<p align="center">
<img align="center" src="../../doc/imgs/xdeepfm.jpg">
<p>
[DCN](https://dl.acm.org/doi/pdf/10.1145/3124749.3124754):
<p align="center">
<img align="center" src="../../doc/imgs/dcn.jpg">
<p>
[DIN](https://dl.acm.org/doi/pdf/10.1145/3219819.3219823):
<p align="center">
<img align="center" src="../../doc/imgs/din.jpg">
<p>
## 使用教程
### 数据处理
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册