Specformer

Specformer copied to clipboard

pygdataclass is required, but it is missing in repo

1

In get_dataset.py ``` from dataclasses import * from dgldataclass import DglGraphPropPredDataset, DglPCQM4Mv2Dataset, DglZincDataset from pygdataclass import PygGraphPropPredDataset ``` dgldataclass.py exists, but pygdataclass.py does not. It might be issue??

teltim

It seems like `dgl.adj` is deprecated after v1.1 and replaced with `dgl.adj_external`.

kaansancak

Problems in the get_dataset file

2

from dataclass import * from pygdataclass import PygGraphPropPredDataset The custom "pygdataclass" and "pygdataclass" modules are not a standard Python package or library. But I can't find the files for these...

unomit

At 950 epochs, the best results on the zinc dataset are still more than 1.4, for a total of just 1,000 epochs

1

The experiment seems to have lost some code files，such as pygdataclass.py ...And what is returned in the SpecformerZINC model is a tuple with a different y size. But the above...

QSNZNJING

I found that some data processing was done during testing on Citeseer, so I tested the performance of GCN on the processed data and obtained an ACC of 84.86 ±...

QiZhang3709

Question about Small and medium model for graph classification

1

Hi, I am interested in your work. But I have a question about your medium_model.py; it seems that in your SpecformerMedium class, you didn't apply ``` mha_eig = self.mha_norm(eig) mha_eig,...

Dbgsaoge

The problem of the logits'shape in the train_epoch function in the dgl_main.py

1

Hi, i am very excited for your work, so i am running your codes. there is a problem for me in the train_epoch function in the dgl_main.py. Actually, in the...

fantasy-zc