Comments (6)
Thanks for your excellent codes, I have some problems with the loss function. what's the difference between the loss function in the class simclr and the loss function in the class of GcnInfomax.
I think the loss in GcnInfomax is the same as DGI (2019 ICLR) which generalizes DeepInfomax (2019 ICLR) from images to graphs. It aims to maximize the mutual information between local patches and the global graph. And GraphCL (or simclr) aims to maximize the mutual information between the augmentations.
from graphcl.
Got it. Thanks again, Mr. You. Maybe I should read more GCL articles and run some experiments to better understand these questions.
from graphcl.
Hi @scottshufe,
Sorry for the late reply. Double augmentations are implemented for experiments except unsupervised_TU due to some implementation issue then (e.g. please refer to https://github.com/Shen-Lab/GraphCL/tree/master/semisupervised_TU).
from graphcl.
Hi, Mr. You @yyou1996. Thanks for your reply. I think I have implemented the code of double augmentations, but I need to figure out the differences between single augmentation and double augmentations...If you have any ideas on this question, I would love to hear your opinion ๐
from graphcl.
Thanks for your excellent codes, I have some problems with the loss function. what's the difference between the loss function in the class simclr and the loss function in the class of GcnInfomax.
from graphcl.
@scottshufe I feel in small datasets it differs little, while things might change in large-scale datasets. The positive or negative influence depends on whether the augmentation is rational for the downstream.
from graphcl.
Related Issues (20)
- Question about the loss function in the transferLearning_MoleculeNet_PPI/chem HOT 1
- About Unsupervised_Cora_Citeseer HOT 1
- Different result about Transfer Learning HOT 2
- ValueError: `MessagePassing.propagate` only supports `torch.LongTensor` of shape `[2, num_messages]` or `torch_sparse.SparseTensor` for argument `edge_index`. HOT 1
- Question about GraphCL HOT 1
- Question About Sungraph HOT 1
- Question about data augmentation HOT 1
- Question about Unsupervised_TU HOT 4
- Unsupervised learning with self created dataset HOT 1
- graph classification HOT 1
- ้ฎ้ข่ฏทๆ HOT 1
- A question about Semisupervised_TU in pre_training HOT 1
- ่ฟ่ก่ฟ็จๆช็ปๆๅฐฑโEarly stopping!โ HOT 1
- Question about Unsupervised_TU experiments details HOT 4
- Question about Unsupervised-TU ''test'' and ''val'' HOT 1
- How to use for Graph Clustering. HOT 1
- information about the datasets HOT 1
- Question about cortex_DIM in net_infomax.py of semisupervised_TU/finetuning HOT 2
- File "/home/test02/code/GraphCL-master/semisupervised_TU/pre-training/feature_expansion.py", line 27, in __init__ super(FeatureExpander, self).__init__('add', 'source_to_target') TypeError: __init__() takes from 1 to 2 positional arguments but 3 were given HOT 1
- Dateset Error HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from graphcl.