GraphMAE issues

The hyper-parameters of transfer learning

3

Thanks for a outstanding work, transfer learning is a very useful setup in this paper. But the performance in the table seems to require appropriate hyperparameters, can you release the...

jiaruHithub

图1(b)

1

您好，图1(b)是什么软件做出的图呀？https://github.com/THUDM/GraphMAE/blob/b14f080c919257b495e3cb6474286d5252d6a635/imgs/fig.png

1090h2400

Node embedding with feature reconstruction

Is it possible to implement Node embedding with the information about its features? After that, reconstruct the node label and features based only on the node embedding?

jpfn2407

Clarification on Inductive Setting in Graph Neural Networks

Dear THUDM, Firstly, I would like to express my sincere gratitude for your efforts. Your work has been immensely helpful. I have a query regarding the implementation of the inductive...

SangwookBaek

how to customize dataset and use pretrain model

i want to use pretained model on my own dataset, could this model use on customize data.

wml1993

你好，我尝试运行你的代码，但是无法下载demo数据集，请问是否有其他方法可以解决？以下是报错 Traceback (most recent call last): File ".\main_graph.py", line 206, in main(args) File ".\main_graph.py", line 140, in main graphs, (num_features, num_classes) = load_graph_classification_dataset(dataset_name, deg4feat=deg4feat) File "F:\MYT\GraphMAE\graphmae\datasets\data_util.py", line 133, in...

YuantingMaSC