-
Hi, I just get a keyword error when running the code based on torch_geometric. The keyword "residul" seems to be type error in the gat.py, from line 56 to 70. Please double check it out.
-
-
您好，我在自己造的数据集上使用模型，训练集、验证集、测试集都是从一个边的数据列表中分出来的，后来发现每个数据集中的节点只有部分重合，导致final_model中的节点向量不全，没法验证和测试，怎么办？
是我的理解哪里有误吗还是数据集构造错了呢。
-
Thanks for the good research.
I have a question about your paper.
As far as I know, there are inductive settings and transductive settings for the zero-shot task.
In the zero-shot classification …
-
作者您好，想请问一下在SimGCL对于训练集中未出现却在测试集中出现的User会怎样处理呢。我在进行测试的时候，发现实际测试的user数量略小于给定的测试集中的user数。例如该数据集测试集中有1w名user，但实际给出的推荐结果只有9740名user。
-
Hello there,
What kind of unlabelled nodes are included in your pseudo-labels? In a transductive setting, e.g. ogbn-arxiv/products, only test/valid nodes are considered unlabelled during training. …
-
In your code:
https://github.com/shule-deng/RFDNet/blob/main/utils.py#L306
You use all the query data to do the attention, so whether this is a transductive method?
-
### 🚀 The feature, motivation and pitch
While we provide the `LightGCN` model, there is an example missing to showcase its use.
**References:**
* https://github.com/pyg-team/pytorch_geometric/dis…
-
Hi @jxgu1016 thank you for your excellent work
I have some questions about the zero-shot settings. I wonder what is the definition of the zero-shot settings. Only the HOI annotations are masked bu…
-
### 🐛 Describe the bug
```
import torch
from torch_geometric.data import Data
from torch_geometric.nn import GCNConv
from torch_geometric.nn import GAE
class GCNEncoder(torch.nn.Module):
…