-
In KG embedding, Link Prediction task, while executing 'python evaluate_transe_transductive.py', pybind11 error is popping out,
------------- link_prediction --------------
effective triplets: 14…
-
parser.add_argument('--train_aug', default='True', help='perform data augmentation or not during training ') ，请问是这个代码吗？True 是使用full data .False不适用Full data?
-
Sorry to disturb you.
I caught a ResourceExhausted whlie running the Code on Tesla K80 with 12GB MemorySize
I just wonder how many MemorySize I Need to Finish the experiment.
Thanks!
-
https://distill.pub/2021/understanding-gnns/#interactive
-
你好，读了您的paper，觉得很是厉害！但是有个地方不是很明白。如果有一个新的需要预测的测试集，是否还要重新加入节点重新跑代码计算，才能预测？关于预测我不是很懂。论文结论中的这段话我也不是很明白。However, a major limitation of this study is that the GCN model is inherently transductive, in which t…
-
## 📚 Documentation
We should demonstrate the power of GNN in inductive learning. That is, when a new node comes to a graph, we can apply GNN to do a good prediction.
-
https://arxiv.org/abs/1706.02216
> Low-dimensional embeddings of nodes in large graphs have proved extremely useful in a variety of prediction tasks, from content recommendation to identifying prot…
-
Hello,
I am interested in your work about the Twitter graph dataset and i'd like to do the same thing on my own side.
I need to know beforehand, how long did it took to run the whole process and…
-
Hi @lmcinnes,
I am trying to use UMAP to show the increasing ability to seperate different classes over the training process of a neural network, similar to [https://medium.com/@rakesh.chada/understa…
-
what is the use of x in load_data function as from what I see it's just loaded and isn't used, but the one used is allx, what are the differences between them.