-
Could you give us a few examples for the classical graph algorithms, such as Pagerank, LPA, WCC, etc.?
-
Hi, I wish to refactor the MAGNN code for my research project.
However, I found that the Link Prediction and Node Classification Tasks used different models (MAGNN_lp, MAGNN_nc, MAGNN_nc_mb) in your …
-
https://arxiv.org/abs/1906.07181
-
Hello authors, can you kindly advise on how the adjacency.txt file has been converted to the adjacency matrix,I do not know julia and will be doing it in Python/Pytorch. I am not getting how the raw d…
-
## ❓ Questions & Help
Hi @rusty1s, I'm using the [GATconv](https://pytorch-geometric.readthedocs.io/en/latest/modules/nn.html#torch_geometric.nn.conv.GATConv) layer in my model. Since my graph is pre…
-
It's a super cool example (particle physicist here!), but i'm not sure if the system actually learns anything. The loss just seems to be fluctuating around random performance on the test set, e.g. 110…
-
In my recent learning, I'm unsure how to caculate $\lambda_l$. In other words, Do you use test dataset nodes in your calculations of label smoothness? If the situation in the traing set is: The two …
-
看论文的model overview，用于训练和预测的应该是经过了GNN之后得到的item embedding，但是代码里是用的第0层的item embedding？作者求解释一下？
-
Hello,
Previously I have node features (of dimension=5), so I am using ```Rs_in = [(5, 0, 1)] ```. Recently I get some new scalar features on edges, I was wondering how to specify these extra edg…
-
I am trying to reproduce the results of your paper and I am having some difficulty.
In case of Maximum Value Difference you show that the MLP gets 9% accuracy. I was able to reproduce this result. …