MuGNN
MuGNN copied to clipboard
thunlp
Source code for ACL2019 paper "Multi-Channel Graph Neural Network for Entity Alignment".
Thank you for sharing the code. I tried it but got an error. Could you please give me a hint about it? 
The true value function is designed to minimize || ei + rij - ej ||p for the embedding of positive triplet samples, and to maximize || ei + rij -...
Hi, I am looking into your code. But it seems that in `models.py`, the `self.multi_head_att_layers`(self-attention) and `self.relation_attention_gcns`(cross-KG attention) use the same adjacency matrix, rather than different adj matrix for each...
