DeepInf

DeepInf copied to clipboard

tanh while calculating attention scores

1

Hey! I was interested into why are you using tanh here: `attn_src = torch.matmul(F.tanh(h_prime), self.a_src) # bs x n_head x n x 1` in [BatchMultiHeadGraphAttention, get_layers.py](https://github.com/xptree/DeepInf/blob/master/src/gat_layers.py#L85). Did it stabilize the...

gordicaleksa

您好，请问您能提供数据集预处理的代码吗？我想尝试将您的方法运用在我自己的数据集上。感谢！

cxyccc

Thank you for your work. In your paper you mentioned that you constructed 6 vertex features, a 64d embedding feature, and 3 ego features. However, after downloading the datasets you...

ZhongLIFR