Comments (4)
To address the problem, you need to provide more details about your training setting and results.
from deepcf.
To address the problem, you need to provide more details about your training setting and results.
I used the same settings(lr=0.0001,epochs=20 and sgd). The results are HR=0.1582 and NDCG=0.0699. I tried to delete the already given pre-train models for ml-1m. Then I execute the CFNet and after 20 epochs(with sgd and lr= 0.0001) I got HR=0.5341 and NDCG=0.3018. I just wanna know that how did you train it for the existing Pre-Train files? I would really appreciate if you can provide the hyperparameter values.
from deepcf.
First, you need to run the following commands to obtain pre-trained models for AMusic:
Run CFNet-rl:
python DMF.py --dataset AMusic --epochs 20
Run CFNet-ml:
python MLP.py --dataset AMusic --epochs 20
Then you can use the pre-trained models to run CFNet, which should yield a comparable result as presented in our paper:
python CFNet.py --dataset ml-1m --epochs 20 --lr 0.0001 --learner sgd --dmf_pretrain PathToYourPretrainedDMFFile --mlp_pretrain PathToYourPretrainedMLPFile
Notice, since AMusic has more items than users, you should use more dimensions for userlayer ([1024, 64]) and fewer dimensions for itemlayer ([512, 64]). You can change it in DMF.py.
from deepcf.
I change the original heading “AMusic results are not accurate.” to “How to use the code on other data sets?” to better fit this issue.
from deepcf.
Related Issues (8)
- Time complexity HOT 1
- DMF and MLP are not right? HOT 2
- error:cannot create a tensor proto whose content is larger than 2GB HOT 2
- Kindly upload the lastfm and AToy data sets as well. HOT 2
- How to preprocess the datasets? HOT 3
- Question about the lastfm dataset HOT 1
- Question about the AMusic dataset HOT 8
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 deepcf.