Wei Jin

icon indicating a website link http://www.cs.emory.edu/~wjin30/

icon company Emory University icon location Atlanta, Georgia icon location Assistant Professor @ Emory University #MachineLearning #GraphNeuralNetworks

Results 63 comments of Wei Jin

The exp result reproduce of the whole dataset on Table 2

Hi, Sorry for the late reply. This is indeed included in the `train_coreset.py` file: https://github.com/ChandlerBang/GCond/blob/9f2032ce576f84ecdf077430367f5e33aa171c28/train_coreset.py#L61-L70 You may run `train_coreset.py` to get the result you want. ``` python train_coreset.py --dataset cora...

questions of the coarsen part

Hey, we use the code provided by [link](https://github.com/szzhang17/Scaling-Up-Graph-Neural-Networks-Via-Graph-Coarsening). We coarsen the training graph while using the original test graph for inference.

questions of the coarsen part

For the transductive setting, the training graph is the same as the full graph (2.7k nodes). Here the ratio `r` means the number of nodes in condensed graphs to that...