Comments (9)
Hi,
Thanks for your interest in our work.
We followed the EigenPool paper and used the random splitting of datasets into 0.8, 0.1, 0.1 for training, validation and testing. The SAGPool paper used the 10-fold validation splitting, which is more reasonable in fact. This is why the baseline results reported by us are relatively higher compared with the original paper.
from hgp-sl.
The key difference lies at the random 10 splittings and 10-fold splittings. The basic difference is that if you use random splittings there is no guarantee to test all the samples in 10 runs. However, in 10-fold splittings, all the samples will be tested once in 10 runs.
I think the difference is very clear.
from hgp-sl.
ok, so your meaning is you do not change the setting of the experiments of the SAGPool Model, only choose 10-fold validation splitting. if convinience, can you pose this part's code, i am following SAGPool model, but do not have this higher accuracy.
Or send email to me ? Please~
thank for your time.
from hgp-sl.
All our experiments are conducted at the random splitting of datasets into 0.8, 0.1, 0.1 for training, validation and testing; NOT the 10-fold validation splitting;
from hgp-sl.
sorry~ maybe i do not understand. i remember in the original paper, the setting of the experiments (SAGPool model), also split the dataset into 0.8 0.1 0.1, what's the difference between yours and the origin?
from hgp-sl.
thank you very much~ i got it!
lastly~ thanks for your time~
from hgp-sl.
You are welcome. If there is any question, please let me know.
Thank you.
from hgp-sl.
hi~ i am coming again~ haha~
can i add your Wechat to ask you some tips for the training model~
from hgp-sl.
Sure, you can leave you Wechat ID and I will add you.
from hgp-sl.
Related Issues (19)
- How to run on DD dataset? HOT 4
- Segmentation error HOT 4
- Predicting Same label for every data in custom dataset HOT 5
- How to draw a graph as beautiful as model.png HOT 2
- Network architecture on D&D and ENZYMES HOT 4
- Question about layers of this model HOT 2
- About the acc from this repo and the paper HOT 15
- How to apply HGP-SL to dense batched adjacency matrix HOT 3
- User defined Dataset HOT 1
- Use of this work for regression and classification HOT 1
- Recurrence experiment HOT 2
- reproducible experiments
- Datasets Division
- Dataset split
- About the GAT model used in this paper HOT 1
- The accuracy is sensitive to random seed.
- The issue about acc HOT 2
- AssertionError assert trust_data or int(col.max()) < N 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 hgp-sl.