-
Hi.It seems you construct hypgraph incidence matrix H from both training data and testing data.
In the function hypergraph_utils.construct_H_with_KNN(),the data pts that fed in seems has both train…
-
Hi,
I was really interested to use your model but unfortunately it is in Tensorflow (or Keras for the unofficial implementation). I propose here the Pytorch version (https://github.com/Diego999/pyG…
-
Does UMAP can be used inside a **High-Frequency** Time Series Forecasting problem?
UMAP is just awesome as an analysis tool, but what about in real-time? I use LSTM to work inside a High-Frequency …
ghost updated
5 years ago
-
where is the code for transductive maml?
-
#### Description
LabelSpreading fails during `predict` when using a callable kernel that returns sparse matrix
`sklearn.semi_supervised.LabelSpreading` allows user to provide a callable as a kerne…
-
I have found paper url from your md file and crawled every paper.
When crawling, i noticed that some paper url that attached inside your md file are wrong...
Here is paper and wrong url.
Oh, …
-
I understand that fastgcn performs sampling on the X in the batch, and it get a subgraph for each sampling. But the graph (the adjacency matrix A) still contains the node of the test set, why it is i…
-
hello,
i ran the code for classification on google colab, downloading files on google drive.
the images folder containing 60,000 images crashes as google drive cannot handle so many files within o…
-
Hi @vuptran,
Thanks for creating this library!
I've got a more general question on retraining, locality and transfer learning.
Say I have a graph G_1, and another graph G_2. And let G_1 > G_2 in …
idanh updated
5 years ago
-
We have already ITransductiveItemRecommender. This interface should be improved and implemented, plus the same for rating prediction.
Then integrate them into the command-line tools.