zeyuwang

Can you provide hyper-parameters for these datasets used in the paper？ In ogb, these datasets doesn't exist.

Thanks a lot! I will try it.

In this paper, you train and finetune five models (contextpred, edgepred, infomax, making and supervised) seperately. Have you ever think about training and finetuning these five aspects simultaneously? May be...

请问哪里修改的程序？我使用带骨骼的数据结果也特别差

@LiJieqin 您好，您之前说的open/close state是什么意思？我也遇到了bone数据准确率很低的问题。

Same question.

Hi:     In your released code, what's the function of file run_training_edge_imp.py and how to get edge_imp_data.npy 、edge_imp_label.npy these two files? ------------------ 原始邮件 ------------------ 发件人: "sgadgil6/cnslab_fmri"

Hi:    I want to learn which conference or magazine do you publish this paper on ?  ------------------ 原始邮件 ------------------ 发件人: "devnkong/FLAG"

python 3.7.7 dgl-cu101 0.4.1 In finetune process, I run 100 epochs. When testing rdt-b dataset, the 100th epoch train_accuracy is 0.991 while the test_accuracy is 0.835 

Have you got complete data？