GraphCL_Automated
GraphCL_Automated copied to clipboard
Shen-Lab
[ICML 2021] "Graph Contrastive Learning Automated" by Yuning You, Tianlong Chen, Yang Shen, Zhangyang Wang; [WSDM 2022] "Bringing Your Own View: Graph Contrastive Learning without Prefabricated D...
Hi! Could you please release your saved model file of transfer learning in JOAO? I mean the weights file that will be used in finetuning of transfer learning.
When i run go.sh with dataset except "NCI1", "PROTEINS", "DD", "MUTAG" i got log like this. Please let me know how to figure out this problem thank you 
The research work is exciting! I noticed that you formulate the automated graph contrastive learning as the min-max optimization problem. May I ask that why not use the bi-level optimization...
Hi, Thanks for your excellent work. I wonder could you please provide the pretrained models on the zinc_standard_agent dataset? Thanks a lot!
Hello, Thank you for this awesome work! I tried to run the pretraining code in the semisupervised setting by running this command (python main_pretrain_graphcl_joao.py --gamma 0.01 --dataset ogbg-molchembl) and it...
The code does not work at runtime because the COLLAB dataset does not have node properties.
This pull request refactors the `FeatureExpander` class in the following ways: - Modularizes noise addition to edges into the `add_noise_to_edges` method. - Modularizes edge removal into the `remove_specified_edges` method. -...
Hello, great work! Could you update the pre-trianed model to reproduce the result?
