Comments (7)
The noise is added by using dropout.
I think the L2 normalization is used to normalize feedback data for solve accommodating user or fastidious user problem.
from vae_cf.
Here 's what I think,
It 's from the problem you will face with explicit feedback: for example, accommodating users rate 3/5 star for item they don't like and 5/5 star for item they like, fastidious users rate 1/5 star for item they don't like and 3/5 star for item they like. So user feedback data can be distorted by some users. So you have to normalize user feedback and that why L2 norm for individual user .
With implicit feedback I think you will face this problem.
And I think when your feedback data is normal distribution or like normal distribution, you don't need normalization.
I have an unrelated question. When using Gaussian, the log likelihood contains confidence c_ij, but not in multinomial likelihood. Can you explain why multinomial doesn't need c_ij?
from vae_cf.
I wonder that also. Since it is a DAE, and I don't see any noise being added to the input, I think the noise is the L2 normalization itself?
from vae_cf.
Can you explain the L2 normalization in other words please? I didnt understand.
And why L2 norm instead of layer/batch norm? Btw, I have implemented it on my own on another dataset and the normalization didn't seem to help.
from vae_cf.
Your explanation makes sense to me. In this case where you have your inputs binary, normalization does not help.
Regarding the other issue, can you point it in the code?
from vae_cf.
In VAE CF paper, the Gaussian log likelihood (Eq 3) contains confidence weight c_ui but not in the Multinomial log likelihood (Eq 2). Can you explain why multinomial doesn't need confidence weight?
And I think in case of binary inputs, your feedback still can be distorted.
from vae_cf.
@jin530 In my opinion,both DAE and VAE ,the author used the structure of denosing ,that is L2 and dropoout,added Bernoulli noise to the input data
from vae_cf.
Related Issues (18)
- Making a script out of the notebook? HOT 2
- One problem reveals when I rerun the program HOT 5
- Error in python 3.5+ HOT 7
- beta annealing
- getting NaN values in ndcg HOT 3
- Normalization of multinomial probability
- Getting Error When importing "import apply_regularization, l2_regularizer" HOT 2
- All kind of measure (Recall, NDCG_binary_at_k_batch) alway return NaN HOT 3
- confused about split data
- Request for Modification: filter_triplets Function
- A question about the way of how to split data HOT 5
- A question about Negative sampling? HOT 10
- Not an issue, just a question about the other datasets HOT 2
- some question HOT 2
- Running on Python 3.5+ HOT 3
- Superscript “PR” means partial regularization or personal ranking? HOT 1
- Implementation of CDAE (as a baseline) HOT 1
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 vae_cf.