GNN-MAGNA
GNN-MAGNA copied to clipboard
xjtuwgt
Hello, thank you for your work! I wonder if you are interested in implementing your model in popular framework: [torch-geometric](https://github.com/pyg-team/pytorch_geometric)? Would be very helpful, thank you!
作者你好，我最近在学习这篇论文，对您提出的新颖的多跳attention GNN十分感兴趣，同时在阅读和复现代码时有一些疑问，能否向您请教一下？ Q1. 模型中对于s的计算只使用了一跳邻居信息，没有获取远跳邻居的信息的模块，多跳如何体现？ Q2. PPR中的Ai是否可以理解为实体1的i跳邻居的注意力分数？同时i是否是一个固定的数值？ Q3. 代码中的top_k是否对应附录设置中的hop_num？其意义是否是只选择部分权重最大的邻居作为一跳邻居？
I use the same hyperparameter as the paper claimed,but got low acc。The experimental results are lower than the original gcn。 `2022-07-19 16:23:15,708 INFO Best validation acc: 0.79 Best test acc:...
Hello author, I'm a student who interested in your works when reading Multi-hop Attention Graph Neural Networks Can I get the information about the hardware that you train your model...
