Skip to content

Commit d40a89d

Browse files
renmadarenmada
committed
Add kim model
2 parents 25a2c9e + f921026 commit d40a89d

File tree

25 files changed

+2071
-139
lines changed

25 files changed

+2071
-139
lines changed

‎README_CN.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -173,7 +173,7 @@ python -u tools/static_trainer.py -m models/rank/dnn/config.yaml # 静态图训
173173
| 排序 | [DCN_V2](models/rank/dcn_v2/) | - | ✓ | ✓ | >=2.1.0 | [WWW 2021][DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems](https://arxiv.org/pdf/2008.13535v2.pdf)|
174174
| 排序 | [DSIN](models/rank/dsin/) | - | ✓ | ✓ | >=2.1.0 | [IJCAI 2019][Deep Session Interest Network for Click-Through Rate Prediction](https://arxiv.org/pdf/1905.06482v1.pdf) |
175175
| 排序 | [SIGN](models/rank/sign/)([文档](https://paddl7erec.readthedocs.io/en/latest/models/rank/sign.html)) | [Python CPU/GPU](https://aistudio.baidu.com/aistudio/projectdetail/3869111) | ✓ | ✓ | >=2.1.0 | [AAAI 2021][Detecting Beneficial Feature Interactions for Recommender Systems](https://arxiv.org/pdf/2008.00404v6.pdf) |
176-
| 多任务 | [AITM](models/rank/aitm/) | - | ✓ | ✓ | >=2.1.0 | [KDD 2021][Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising](https://arxiv.org/pdf/2105.08489v2.pdf) |
176+
| 排序 | [IPRec](models/rank/iprec/)([文档](https://paddl7erec.readthedocs.io/en/latest/models/rank/iprec.html)) | - | ✓ | ✓ | >=2.1.0 | [SIGIR 2021][Package Recommendation with Intra- and Inter-Package Attention Networks](http://nlp.csai.tsinghua.edu.cn/~xrb/publications/SIGIR-21_IPRec.pdf) | 多任务 | [AITM](models/rank/aitm/) | - | ✓ | ✓ | >=2.1.0 | [KDD 2021][Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising](https://arxiv.org/pdf/2105.08489v2.pdf) |
177177
| 多任务 | [PLE](models/multitask/ple/)([文档](https://paddlerec.readthedocs.io/en/latest/models/multitask/ple.html)) | [Python CPU/GPU](https://aistudio.baidu.com/aistudio/projectdetail/3238938) | ✓ | ✓ | >=2.1.0 | [RecSys 2020][Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations](https://dl.acm.org/doi/abs/10.1145/3383313.3412236) |
178178
| 多任务 | [ESMM](models/multitask/esmm/)([文档](https://paddlerec.readthedocs.io/en/latest/models/multitask/esmm.html)) | [Python CPU/GPU](https://aistudio.baidu.com/aistudio/projectdetail/3238583) | ✓ | ✓ | >=2.1.0 | [SIGIR 2018][Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate](https://arxiv.org/abs/1804.07931) |
179179
| 多任务 | [MMOE](models/multitask/mmoe/)([文档](https://paddlerec.readthedocs.io/en/latest/models/multitask/mmoe.html)) | [Python CPU/GPU](https://aistudio.baidu.com/aistudio/projectdetail/3238934) | ✓ | ✓ | >=2.1.0 | [KDD 2018][Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts](https://dl.acm.org/doi/abs/10.1145/3219819.3220007) |

‎README_EN.md‎

Lines changed: 211 additions & 0 deletions
Large diffs are not rendered by default.

‎application/multitask_on_video/readme.md‎

Lines changed: 567 additions & 0 deletions
Large diffs are not rendered by default.

‎datasets/iprec/run.sh‎

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
1+
mkdir whole_data
2+
mkdir whole_data/train && mkdir whole_data/test
3+
wget https://paddlerec.bj.bcebos.com/datasets/IPREC/3_days.zip
4+
unzip 3_days.zip
5+
mv train.jsonl whole_data/train
6+
mv test.jsonl whole_data/test

‎doc/imgs/iprec.png‎

464 KB
Loading

‎doc/source/models/rank/iprec.md‎

Lines changed: 73 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,73 @@
1+
# iprec模型
2+
代码请参考：[AITM](https://github.com/PaddlePaddle/PaddleRec/tree/master/models/rank/iprec)
3+
如果我们的代码对您有用，还请点个star啊~
4+
注：在阅读该示例前，建议您先了解以下内容：
5+
6+
[paddlerec入门教程](https://github.com/PaddlePaddle/PaddleRec/blob/master/README.md)
7+
8+
## 内容
9+
10+
- [模型简介](#模型简介)
11+
- [数据准备](#数据准备)
12+
- [运行环境](#运行环境)
13+
- [快速开始](#快速开始)
14+
- [模型组网](#模型组网)
15+
- [效果复现](#效果复现)
16+
- [进阶使用](#进阶使用)
17+
- [FAQ](#FAQ)
18+
19+
## 模型简介
20+
Package Recommendation with Intra- and Inter-Package Attention Networks 《利用“包内”和“包间”注意力网络的包推荐》。
21+
随着移动互联网中在线社交网络的蓬勃发展，我们提出了一个新颖的社交推荐场景，名为Package Recommendation。在这种场景中，用户不再被推荐单个项目或项目列表，而是被推荐异构且类型多样对象的组合（称为包，例如，包括新闻、媒体和观看新闻的朋友）。与传统推荐不同，在包推荐中，包中的对象被明确显示给用户，用户会对显式展示的对象表现出极大的兴趣，反过来这些对象可能对用户行为产生重大影响，并显著改变传统的推荐模式。
22+
23+
## 数据准备
24+
训练及测试数据集选自时间窗口为3天的微信公众号的用户日志，按7:1:2划分训练集、验证集、测试集
25+
在模型目录的data目录下为您准备了快速运行的示例数据，若需要使用全量数据可以参考下方效果复现部分。
26+
## 运行环境
27+
PaddlePaddle>=2.0
28+
29+
python 2.7/3.5/3.6/3.7
30+
31+
os : windows/linux/macos
32+
33+
## 快速开始
34+
本文提供了样例数据可以供您快速体验，在任意目录下均可执行。在iprec模型目录的快速执行命令如下：
35+
```bash
36+
# 进入模型目录
37+
# cd models/rank/iprec # 在任意目录均可运行
38+
# 动态图训练
39+
python -u ../../../tools/trainer.py -m config.yaml # 全量数据运行config_bigdata.yaml
40+
# 动态图预测
41+
python -u ../../../tools/infer.py -m config.yaml
42+
```
43+
## 模型组网
44+
模型整体结构如下：
45+
46+
<img align="center" src="../../../imgs/iprec.png">
47+
48+
## 效果复现
49+
为了方便使用者能够快速的跑通每一个模型，我们在每个模型下都提供了样例数据。如果需要复现readme中的效果,请按如下步骤依次操作即可。
50+
在全量数据下模型的指标如下：
51+
52+
| 模型 | auc | batch_size | epoch_num| Time of each epoch |
53+
|:------|:-------| :------ | :------| :------ |
54+
| iprec | 0.6934 | 256 | 1 | 3600s |
55+
56+
1. 确认您当前所在目录为PaddleRec/models/rank/iprec
57+
2. 进入Paddlerec/datasets/iprec
58+
59+
``` bash
60+
cd ../../../datasets/iprec
61+
sh run.sh
62+
```
63+
3. 切回模型目录,执行命令运行全量数据
64+
65+
```bash
66+
cd - # 切回模型目录
67+
python -u ../../../tools/trainer.py -m config_bigdata.yaml
68+
python -u ../../../tools/infer.py -m config_bigdata.yaml
69+
```
70+
71+
## 进阶使用
72+
73+
## FAQ

‎doc/source/readme.md‎

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -50,4 +50,5 @@
5050
[autofis](https://paddlerec.readthedocs.io/en/latest/models/rank/autofis.html)
5151
[aitm](https://paddlerec.readthedocs.io/en/latest/models/rank/aitm.html)
5252
[dsin](https://paddlerec.readthedocs.io/en/latest/models/rank/dsin.html)
53-
[sign](https://paddlerec.readthedocs.io/en/latest/models/rank/sign.html)
53+
[sign](https://paddlerec.readthedocs.io/en/latest/models/rank/sign.html)
54+
[iprec](https://paddlerec.readthedocs.io/en/latest/models/rank/iprec.html)

‎models/rank/iprec/config.yaml‎

Lines changed: 46 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,46 @@
1+
# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
2+
#
3+
# Licensed under the Apache License, Version 2.0 (the "License");
4+
# you may not use this file except in compliance with the License.
5+
# You may obtain a copy of the License at
6+
#
7+
# http://www.apache.org/licenses/LICENSE-2.0
8+
#
9+
# Unless required by applicable law or agreed to in writing, software
10+
# distributed under the License is distributed on an "AS IS" BASIS,
11+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+
# See the License for the specific language governing permissions and
13+
# limitations under the License.
14+
15+
runner:
16+
train_data_dir: "./data/sample_data/train"
17+
train_reader_path: "reader" # importlib format
18+
train_batch_size: 5
19+
model_save_path: "output_model_iprec"
20+
use_auc: True
21+
use_gpu: False
22+
epochs: 1
23+
print_interval: 1
24+
test_data_dir: "./data/sample_data/test"
25+
infer_reader_path: "reader" # importlib format
26+
infer_batch_size: 5
27+
infer_load_path: "output_model_iprec"
28+
infer_start_epoch: 0
29+
infer_end_epoch: 1
30+
31+
hyper_parameters:
32+
optimizer:
33+
class: adam
34+
learning_rate: 0.0001
35+
num_users: 554237
36+
num_items: 344087
37+
num_bizs: 166465
38+
hidden_units: 64
39+
f_max_len: 20
40+
k: 4
41+
u_max_i: 99
42+
u_max_f: 220
43+
u_max_pack: 50
44+
pack_max_nei_b: 20
45+
pack_max_nei_f: 20
46+
dropout_rate: 0.4

‎models/rank/iprec/config_bigdata.yaml‎

Lines changed: 47 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,47 @@
1+
# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
2+
#
3+
# Licensed under the Apache License, Version 2.0 (the "License");
4+
# you may not use this file except in compliance with the License.
5+
# You may obtain a copy of the License at
6+
#
7+
# http://www.apache.org/licenses/LICENSE-2.0
8+
#
9+
# Unless required by applicable law or agreed to in writing, software
10+
# distributed under the License is distributed on an "AS IS" BASIS,
11+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+
# See the License for the specific language governing permissions and
13+
# limitations under the License.
14+
15+
runner:
16+
train_data_dir: "../../../datasets/iprec/whole_data/train"
17+
train_reader_path: "reader" # importlib format
18+
train_batch_size: 256
19+
model_save_path: "output_model_iprec_all"
20+
use_auc: True
21+
use_gpu: True
22+
epochs: 5
23+
print_interval: 500
24+
25+
test_data_dir: "../../../datasets/iprec/whole_data/test"
26+
infer_reader_path: "reader" # importlib format
27+
infer_batch_size: 256
28+
infer_load_path: "output_model_iprec_all"
29+
infer_start_epoch: 0
30+
infer_end_epoch: 5
31+
32+
hyper_parameters:
33+
optimizer:
34+
class: adam
35+
learning_rate: 0.0001
36+
num_users: 554237
37+
num_items: 344087
38+
num_bizs: 166465
39+
hidden_units: 64
40+
f_max_len: 20
41+
k: 4
42+
u_max_i: 99
43+
u_max_f: 220
44+
u_max_pack: 50
45+
pack_max_nei_b: 20
46+
pack_max_nei_f: 20
47+
dropout_rate: 0.4

0 commit comments

Comments
 (0)