刘致远
Hi, These two models use adjs with the same connectivity. But the edge weights are calculated by KG Self-Attention and Cross-KG Attention module separately in two channels.
Thanks for the notification. I have updated the link in case it has expired. Can you retry the link in the readme file?
也许可以增加修改发送快捷键的选项，使用Enter换行，使用Ctrl + Enter发送
Same issue here. Here is the full error report while running ./run_dqn.sh ```txt (py27) zyliu@next-dgx1-01:~/code/graph_adversarial_attack/code/graph_attack$ ./run_dqn.sh -phase train ====== begin of s2v configuration ====== | msg_average = 0 ====== end...
Actually, for `run_grad.sh`, we can simply comment the 17th line of `grad_attack.py` and the code would be good to run.
Hi, can you try the rdflib version in the readme file?