Comments (8)
Okay, I have found his code before, but that code is poorly written and runs so slow. So I decided to reimplement my own version of GraphRec which performs bad. I also asked the authors for the whole datasets using in that paper but received no reply. According to what you say, I guess it probably doesn't work as reported in his paper. Maybe I should stop wasting time on GraphRec. Thanks for your help.
from qrec.
Well...
I have also tried to run his released code of Graph Neural Network for Social Recommendation. I guess it needs several days to train GraphRec with the whole dataset used in his/her paper...
And I have requested for the code of Deep Adversarial Social Recommendation more than twice but received no reply. BTW, is this the work you said that didn't work for you?
from qrec.
Thanks for you guys.
from qrec.
Well... actually I have implemented the released code of GraphRec and I must say that the results are almost as same as their reported ones.
from qrec.
I am questioning the IJCAI'19 paper. The results of the www'19 paper might be reproducible. Even so, I found the author closed the issue tab of the repo, which is interesting. As for other papers, you would never receive any replies from him if you try to ask for the implementations via email. Personally, I hold a very negative view of his work.
from qrec.
I see~ also one thing is really interested me is that the author published 1, DSCF(RecSys19), 2, GraphRec(WWW19),3, DeepSoR(WWW2018) at ALMOST the same period, its quite fast, fast as abnormal.. the second thing is, these three paper use almost same baseline models, the only change is they are trying to compare the model developed by themselves(i mean the same author), I think its easy and tricky. BTW, only the code of GraphRec is released, I guess the author is confident about graphRec(although other people wont think so), but less confident about neither DSCF and DeepSoR...
from qrec.
The fast pace is not the problem. Refusing to release the codes is. Anyway, I would not be serious to his work.
from qrec.
The fast pace is not the problem. Refusing to release the codes is. Anyway, I would not be serious to his work.
you are right
from qrec.
Related Issues (20)
- RSGAN中负样本生成的问题 HOT 1
- 使用GPU HOT 2
- K重交叉验证每一次结果不一样 HOT 2
- About socialmf_tf HOT 2
- DHCF模型 HOT 2
- Problem HOT 1
- NDCG计算 HOT 1
- 数据集问题 HOT 1
- 关于MHCN的性能问题 HOT 1
- 关于ESRF的问题请教 HOT 6
- Visual image rendering HOT 2
- Performance comparison over different item groups HOT 3
- yelp数据集的疑问 HOT 1
- 用相同的数据集训练,设置相同的种子,相同的参数。MHCN在QRec上的表现明显优于SELFRec是什么原因啊 HOT 5
- 关于ESRF代码如何提取出 alternative neighborhood HOT 3
- KeyError: 1 HOT 8
- 更改训练集和测试集 HOT 4
- 有关新模型训练 HOT 1
- 如何配置evaluation.setup下的-predict参数 HOT 2
- 可视化结果 HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from qrec.