提交 7aef156b 编写于 作者: M malin10

Merge branch 'doc' into 'develop'

update recall/match readme

See merge request !42
......@@ -25,6 +25,18 @@
| DSSM | Deep Structured Semantic Models | [Learning Deep Structured Semantic Models for Web Search using Clickthrough Data](https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/cikm2013_DSSM_fullversion.pdf)(2013) |
| MultiView-Simnet | Multi-view Simnet for Personalized recommendation | [A Multi-View Deep Learning Approach for Cross Domain User Modeling in Recommendation Systems](https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/frp1159-songA.pdf)(2015) |
下面是每个模型的简介(注:图片引用自链接中的论文)
[DSSM](https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/cikm2013_DSSM_fullversion.pdf):
<p align="center">
<img align="center" src="../../doc/imgs/dssm.png">
<p>
[MultiView-Simnet](https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/frp1159-songA.pdf):
<p align="center">
<img align="center" src="../../doc/imgs/multiview-simnet.png">
<p>
## 使用教程
### 数据处理
### 训练
......
# 召回模型库
## 简介
我们提供了常见的召回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。实现的召回模型包括 [SR-GNN](http://gitlab.baidu.com/tangwei12/paddlerec/tree/develop/models/recall/gnn)[GRU4REC](http://gitlab.baidu.com/tangwei12/paddlerec/tree/develop/models/recall/gru4rec)[Sequence Semantic Retrieval Model](http://gitlab.baidu.com/tangwei12/paddlerec/tree/develop/models/recall/ssr) [Tree-based Deep Model](http://gitlab.baidu.com/tangwei12/paddlerec/tree/develop/models/recall/tdm)[Word2Vector](http://gitlab.baidu.com/tangwei12/paddlerec/tree/develop/models/recall/word2vec)
我们提供了常见的召回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。实现的召回模型包括 [SR-GNN](http://gitlab.baidu.com/tangwei12/paddlerec/tree/develop/models/recall/gnn)[GRU4REC](http://gitlab.baidu.com/tangwei12/paddlerec/tree/develop/models/recall/gru4rec)[Sequence Semantic Retrieval Model](http://gitlab.baidu.com/tangwei12/paddlerec/tree/develop/models/recall/ssr)[Word2Vector](http://gitlab.baidu.com/tangwei12/paddlerec/tree/develop/models/recall/word2vec)
模型算法库在持续添加中,欢迎关注。
......@@ -22,21 +22,38 @@
| 模型 | 简介 | 论文 |
| :------------------: | :--------------------: | :---------: |
| GNN | SR-GNN | [Session-based Recommendation with Graph Neural Networks](https://arxiv.org/abs/1811.00855)(2018) |
| Word2Vec | word2vector | [Distributed Representations of Words and Phrases and their Compositionality](https://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf)(2013) |
| GRU4REC | SR-GRU | [Session-based Recommendations with Recurrent Neural Networks](https://arxiv.org/abs/1511.06939)(2015) |
| SSR | Sequence Semantic Retrieval Model | [Multi-Rate Deep Learning for Temporal Recommendation](http://sonyis.me/paperpdf/spr209-song_sigir16.pdf)(2016) |
| TDM | Tree-based Deep Model | [Learning Tree-based Deep Model for Recommender Systems](https://arxiv.org/pdf/1801.02294.pdf)(2018) |
| Word2Vec | word2vector | [Distributed Representations of Words and Phrases and their Compositionality](https://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf)(2013) |
| GNN | SR-GNN | [Session-based Recommendation with Graph Neural Networks](https://arxiv.org/abs/1811.00855)(2018) |
下面是每个模型的简介(注:图片引用自链接中的论文)
[Word2Vec](https://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf):
<p align="center">
<img align="center" src="../../doc/imgs/word2vec.png">
<p>
[GRU4REC](https://arxiv.org/abs/1511.06939):
<p align="center">
<img align="center" src="../../doc/imgs/gru4rec.png">
<p>
[SSR](http://sonyis.me/paperpdf/spr209-song_sigir16.pdf):
<p align="center">
<img align="center" src="../../doc/imgs/ssr.png">
<p>
[GNN](https://arxiv.org/abs/1811.00855):
<p align="center">
<img align="center" src="../../doc/imgs/gnn.png">
<p>
## 使用教程
### 数据处理
```shell
sh data_process.sh
```
### 训练
```shell
python -m paddlerec.run -m config.yaml -d cpu -e single
```
### 预测
## 效果对比
......@@ -47,7 +64,6 @@ python -m paddlerec.run -m config.yaml -d cpu -e single
| DIGINETICA | GNN | -- | 0.507 |
| RSC15 | GRU4REC | -- | 0.67 |
| RSC15 | SSR | -- | 无 |
| - | TDM | -- | -- |
| 1 Billion Word Language Model Benchmark | Word2Vec | -- | 0.54 |
## 分布式
......@@ -57,5 +73,4 @@ python -m paddlerec.run -m config.yaml -d cpu -e single
| DIGINETICA | GNN | -- | -- | -- | -- |
| RSC15 | GRU4REC | -- | -- | -- | -- |
| RSC15 | SSR | -- | -- | -- | -- |
| - | TDM | -- | -- | -- | -- |
| 1 Billion Word Language Model Benchmark | Word2Vec | -- | -- | -- | -- |
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