LIU, Jinyang

How do you train GCN on such a large dataset "Amazon-Book"?

6

The dataset Amazon-Book has 2, 984, 108 interactions, i.e., edges, which is very large. So, how do you train GC-MC (GCN) ? As far as I know, GCN need to...

您好，请问能分享一下track2的数据吗？

8

您好，我想使用比赛的数据学习一下，但是官方数据集现在已经无法下载，能否分享一下下面的三个数据，谢谢！ 

请问有比赛的数据吗？

2

官网的链接已经失效，请问可以分享一下比赛的数据吗，track2，谢谢！

Confused by the loss function.

2

In your code, you minimized `-(oloss + nloss).mean()` which means (oloss+nloss) should be large. So, "oloss become large and nloss become small " is expected. Although -(oloss+nloss) decrease, I got...

The data preprocessing scripts are unable to run

1

The data preprocessing scripts are unable to run, could you please double-check your code?

How do you choose the optimal hyper-parameters?

2

There are several hyper parameters existing: 1. teacher model hyper parameters 2. student model hyper parameters 3. KD hyper parameters (e.g., balance weight for different losses) 4. Training hyper parameters...

Error loading HDFS dataset.

2

Thanks for your great work. As HDFS labels are initially strings, is this a typo in the following line? token[1] are strings, which cannot be converted to int. https://github.com/YangLin-George/PLELog/blob/fd35d79c9bd38b2d087e2241d5a942113013640a/preprocessing/dataloader/HDFSLoader.py#L199

请问为什么需要初始化为[-0.5/ebd_size,-0.5/ebd_size]

2

如题，这样做有什么好处吗？ 谢谢！