deepsnap

deepsnap copied to clipboard

Hi, in the Inductive Link Prediction Split section of [this colab notebook](https://colab.research.google.com/drive/1ycdlJuse7l2De7wi51lFd_nCuaWgVABc?usp=sharing#scrollTo=OB34ecnHTh_I), I see we're making copies of the input graph to help set up the train / val /...

drewdrewdrewdrew

How to convert pyTorch-Geometric custom datasets into DeepSnap datasets?

1

Hello, I am trying to use a custom dataset for link prediction, What i tried was ``` pyg_dataset = My_Own_Dataset() graphs1 = GraphDataset.pyg_to_graphs(pyg_dataset) #error here ``` but i am getting...

ajith01

I made a PyG heterograph as below. ``` cipdata Out[145]: HeteroData( card={ x=[13752, 302] }, user={ x=[10996, 304] }, (user, solved, card)={ edge_index=[2, 28992], edge_attr=[28992] }, (card, rev_solved, user)={ edge_index=[2,...

Jeriousman

Hello, I am trying to reproduce the examples for heterogeneous link prediction but using multiples graphs, i.e. with inductive split. Is there any resources or guidance to implement a model...

lzanellac

Hi, I'm getting an error in the function `num_nodes` because sometimes `self.G` is a list. https://github.com/snap-stanford/deepsnap/blob/6197dcefc7934c6019fe2f4b0aada562e6c17c7d/deepsnap/graph.py#L220 Would it possible to update such function and just return the length of the...

psanch21

Performance issues with ogbl-biokg graph in DeepSNAP

1

Hello, I am trying to use the ogbl-biokg ([docs](https://ogb.stanford.edu/docs/linkprop/#ogbl-biokg) | [github](https://github.com/snap-stanford/ogb)) with the DeepSNAP package. The graph has 5.088.434 edges and 93.773 nodes. I created a custom dataset ([link to...

sophiakrix

I am using the cora link prediction as shown in the example colab: https://colab.research.google.com/drive/1ycdlJuse7l2De7wi51lFd_nCuaWgVABc?usp=sharing Instead of using the cora dataset, I am using a subset of the pokec dataset with...

tomasonjo

How to split a heterogeneous graph for link_pred targeting specific edge_type?

2

Hi I want to split a heterogeneous graph into train, dev, and test set for link_pred, but I need to have the positive and negative instances of the edges/links from...

SohaK

Using the ogbl-biokg with DeepSNAP

4

Hi there! I was just trying out to use the ogbl-biokg graph with DeepSNAP, more precisely using it as input for the [link_prediction.py](https://github.com/snap-stanford/deepsnap/blob/master/examples/link_prediction_hetero/link_prediction.py) for heterogeneous graphs. Since deepSNAP requires a...

sophiakrix

Tested in hetero link prediction code with appropriate changes.

rijulizer