# mkr-recommendation
MKR is a Multi-task learning approach for Knowledge graph enhanced Recommendation. MKR consists of two parts: the recommender system (RS) module and the knowledge graph embedding (KGE) module. The two modules are bridged by cross&compress units, which can automatically learn high-order interactions of item and entity features and transfer knowledge between the two tasks.
![framework](https://github.com/demomagic/mkr-recommendation/blob/master/img/framework.png)
# Usage
For movie:
python preprocess.py -d movie
python main.py -dataset movie
python predict_test.py -d movie # Testing the .pd model
For book:
python preprocess.py -d book
python main.py -dataset book
python predict_test.py -d book # Testing the .pd model
For music:
python preprocess.py -d music
python main.py -dataset music
python predict_test.py -d music # Testing the .pd model
# File structure
* model/
* movie/, book/, music/
* restore/: model save recovery save/restore method, use it to restore model weights
* result/: save the .pd model, deploy model using tensorflow serving
* vocab/: save the embedding, in order to transfer weight, use it for iterative training if new users or new movie/music/book join
* data/
* book/
* BX-Book-Ratings.csv: raw rating file of Book-Crossing dataset
* item_index2entity_id.txt: the mapping from item indices in the raw rating file to entity IDs in the KG
* kg.txt: knowledge graph file
* movie/
* item_index2entity_id.txt: the mapping from item indices in the raw rating file to entity IDs in the KG
* kg.txt: knowledge graph file
* ratrings.dat: raw rating file of MovieLens-1M
* music/
* item_index2entity_id.txt: the mapping from item indices in the raw rating file to entity IDs in the KG
* kg.txt: knowledge graph file
* user_artists.dat: raw rating file of Last.FM
# Reference
[hwwang55/MKR](https://github.com/hwwang55/MKR)
[Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation. In Proceedings of The 2019 Web Conference (WWW 2019)](https://arxiv.org/abs/1901.08907)
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
【资源说明】 毕业设计 基于Python+Django+Scrapy知识图谱的音乐推荐系统的设计与实现+全部资料齐全+部署文档.zip 【备注】 1、该项目是高分毕业设计项目源码,已获导师指导认可通过,答辩评审分达到95分 2、该资源内项目代码都经过测试运行成功,功能ok的情况下才上传的,请放心下载使用! 3、本项目适合计算机相关专业(如软件工程、计科、人工智能、通信工程、自动化、电子信息等)的在校学生、老师或者企业员工下载使用,也可作为毕业设计、课程设计、作业、项目初期立项演示等,当然也适合小白学习进阶。 4、如果基础还行,可以在此代码基础上进行修改,以实现其他功能,也可直接用于毕设、课设、作业等。 欢迎下载,沟通交流,互相学习,共同进步!
资源推荐
资源详情
资源评论
收起资源包目录
毕业设计 基于Python+Django+Scrapy知识图谱的音乐推荐系统的设计与实现+全部资料齐全+部署文档.zip (454个子文件)
.babelrc 460B
.babelrc 402B
scrapy.cfg 269B
checkpoint 73B
reset.css 1KB
user_artists.dat 1.12MB
mkr.ckpt.data-00000-of-00001 11.84MB
variables.data-00000-of-00001 11.84MB
张昕宇_毕业设计.doc 3.53MB
~$宇_毕业设计.doc 162B
.editorconfig 147B
.editorconfig 147B
.eslintignore 51B
.eslintrc 58B
loading.gif 19KB
.gitattributes 43B
.gitignore 213B
.gitignore 154B
.gitignore 38B
.gitignore 14B
.gitkeep 0B
.gitkeep 0B
index.html 2KB
index.html 302B
favicon.ico 1KB
MusicRec.iml 1KB
bysj.iml 724B
NetCloudMusic.iml 467B
mkr.ckpt.index 2KB
variables.index 2KB
bookcode.jpg 38KB
webpack.prod.conf.js 7KB
webpack.prod.conf.js 5KB
playlist.js 4KB
artist.js 3KB
rankingList.js 3KB
user.js 3KB
index.js 3KB
webpack.dev.conf.js 3KB
webpack.dev.conf.js 3KB
webpack.base.conf.js 3KB
utils.js 3KB
utils.js 3KB
index.js 2KB
webpack.base.conf.js 2KB
index.js 2KB
playList.js 2KB
user.js 2KB
tool.js 2KB
axios.js 2KB
runner.js 2KB
dj.js 1KB
song.js 1KB
request.js 1KB
main.js 1KB
check-versions.js 1KB
check-versions.js 1KB
home.js 1KB
build.js 1KB
build.js 1KB
mv.js 1KB
api.js 1KB
login.js 1KB
nightwatch.conf.js 1KB
debounce.js 972B
index.js 922B
search.js 899B
permission.js 870B
.eslintrc.js 790B
index.js 771B
elementCount.js 765B
jest.conf.js 725B
album.js 709B
fetch.js 650B
main.js 593B
test.js 561B
vue-loader.conf.js 559B
vue-loader.conf.js 553B
getters.js 486B
comment.js 362B
HelloWorld.spec.js 348B
index.js 276B
.postcssrc.js 246B
.postcssrc.js 246B
index.js 227B
dev.env.js 195B
dev.env.js 156B
test.env.js 149B
prod.env.js 61B
prod.env.js 61B
setup.js 56B
linkBase.js 49B
bus.js 46B
sing_sim.json 133B
song_sim.json 133B
user_song_prefer.json 133B
singer_sim_singer.json 133B
user_playlist_prefer.json 133B
song_tag.json 132B
sing_song.json 131B
共 454 条
- 1
- 2
- 3
- 4
- 5
资源评论
不走小道
- 粉丝: 3221
- 资源: 5113
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功