tk-rusch / gradientgating Goto Github PK

First of all, thank you for your paper and codes, it really helps me a lot.
Actually, I have a question about your code. This is the code of your model.

class G2_GNN(nn.Module):
    def __init__(self, nfeat, nhid, nclass, nlayers, conv_type='GCN', p=2., drop_in=0, drop=0, use_gg_conv=True):
        super(G2_GNN, self).__init__()
        self.conv_type = conv_type
        self.enc = nn.Linear(nfeat, nhid)
        self.dec = nn.Linear(nhid, nclass)
        self.drop_in = drop_in
        self.drop = drop
        self.nlayers = nlayers
        if conv_type == 'GCN':
            self.conv = GCNConv(nhid, nhid)
            if use_gg_conv == True:
                self.conv_gg = GCNConv(nhid, nhid)
        elif conv_type == 'GAT':
            self.conv = GATConv(nhid,nhid,heads=4,concat=True)
            if use_gg_conv == True:
                self.conv_gg = GATConv(nhid,nhid,heads=4,concat=True)
        else:
            print('specified graph conv not implemented')

        if use_gg_conv == True:
            self.G2 = G2(self.conv_gg,p,conv_type,activation=nn.ReLU())
        else:
            self.G2 = G2(self.conv,p,conv_type,activation=nn.ReLU())

    def forward(self, data):
        X = data.x
        n_nodes = X.size(0)
        edge_index = data.edge_index
        X = F.dropout(X, self.drop_in, training=self.training)
        X = torch.relu(self.enc(X))

        for i in range(self.nlayers):
            if self.conv_type == 'GAT':
                X_ = F.elu(self.conv(X, edge_index)).view(n_nodes, -1, 4).mean(dim=-1)
            else:
                X_ = torch.relu(self.conv(X, edge_index))
            tau = self.G2(X, edge_index)
            X = (1 - tau) * X + tau * X_
        X = F.dropout(X, self.drop, training=self.training)

        return self.dec(X)

I thought n-layers was the number of layers. But when I looked at the code, I realized that it means that one layer is used as nlayers. I think this means that whether I insert the number of layer such as 16 or 32, the number of layer is always one.
May I ask why you implement the code like this? or Did I misunderstand?

And I also want to ask, if I want to check the model performance, what is the order of the Model, do I just pile the layer G2 up?

Dear authors,

Thanks for the awesome work and sharing the code. I noticed that the hyperparameters were set based on random search. Can you also kindly share the hyperparameter setting used in 'run_GNN.py' including:
--GNN, --nhid, --nlayers, --lr, --drop_in, --drop, --weight_decay, --G2_exp
for the following datasets:
Texas, Wisconsin, Cornell, Cora, Citeseer, Pubmed.

Thank you so much!

Dear authors,

Thanks for the awesome work and sharing the code. I noticed that the hyperparameters were set based on random search. Can you also kindly share the hyperparameter setting used in 'run_GNN.py' including:
--GNN, --nhid, --nlayers, --lr, --drop_in, --drop, --weight_decay, --G2_exp
for the following datasets:
Texas, Wisconsin, Cornell, Cora, Citeseer, Pubmed.

Thank you so much!

def get_data(hom_level=0, graph=1):
  seed = 123456
  dataset = Planetoid('../data', 'Cora')

  if(hom_level==0):
    loader = np.load('data/h0.0' + str(round(hom_level, 3)) + '-r' + str(graph) + '.npz')
  else:
    loader = np.load('data/h0.'+str(round(hom_level,3))+'-r'+str(graph)+'.npz')

I was trying to find the .npz file but there is no explanation about the .npz file.
And also i try to understand about the hom_level, but there is no usage of hom_level.
Can you tell me how to deal with these problem?

Great paper and code, thankd for it! I was wondering if you have resources or code available on how the dirichlet energy as well as the MAD was calculated, for reproducibility purposes?

Hi Rusch,

This is a really exciting work! I tried to reproducing the results (on heterophilic graphs) in paper, but I failed and found that the results are much worse than the results in paper. Can you provide the detailed settings for reproducing the results?