wubo2180

Dataset is available at the website [http://www.openslr.org/12/](url)

Dataset is available at the website [http://www.openslr.org/12/](url)

Thanks a lot! That is what I expect.

You may change `x = self.weight_linear(x).view(-1, self.heads, self.emb_dim)` to `x = self.weight_linear(x)`. And add `x_i=x_i.view(-1, self.heads, self.emb_dim)`,`x_j=x_j.view(-1, self.heads, self.emb_dim)` in function `def message(self, edge_index, x_i, x_j, edge_attr):`. The whole code...

Thanks. However, there are some mistakes when the GNN type is gcn, graphsage or gat (gin is OK). Error: ``` /model_chem.py , line 376, in forward self_loop_attr[:, 7] = 1...

By the way, there are some mistaks in util.py `L2P-GNN/code/util.py", line 31, in __call__ i, _, k = structured_negative_sampling(data.edge_index) NameError: name structured_negative_sampling is not defined`