deepsnap

deepsnap copied to clipboard

Illegal instruction (core dumped)

5

I installed deepsnap on a remote machine using pip, with the below dependencies first: PyTorch --> https://pytorch-geometric.readthedocs.io/en/latest/notes/installation.html NetworkX --> https://github.com/networkx/networkx But when I import: from deepsnap.graph import Graph I get:...

ntnn19

Hi, I am trying to reproduce the examples for heterogeneous node classification but with multiples graphs, i.e. with an inductive split. Is there any resource to implement a model with...

itsakk

Architecture of the aggregation in HeteroSAGEConv?

1

Hello! Not really an issue but I have a question about the implementation of the update step in hetero_gnn.py. What is the benefit of calculating the output via [these lines](https://github.com/snap-stanford/deepsnap/blob/master/deepsnap/hetero_gnn.py#L90-#L93):...

anniekmyatt

Default 'remove_self_loops' set to True in heterogeneous link prediction example problematic for use case with multiple node types?

2

Hello, I am working on setting up link prediction on a heterogeneous graph with different node types and used the examples in `deepsnap/examples/link_prediction_hetero` as a starting point. In these examples,...

anniekmyatt

Dimension (Mis)matching - What's the correct usage of DeepSnap Heterogeneous Graph Convolution?

1

I'm sorry I didn't find a good example code or documentation online that I can follow. In example code below, how come the GNN didn't require a dimension 200/350/800 input?...

yrf1

Citing

1

Could you add a bibentry so we can cite the framework?

benedekrozemberczki

mostly cosmetic, adding some type hints, and clarifying comments

4

amirziai

what is deepsnap.dataset.EnsembleGenerator?

1

I couldn't find the detailed tutorial of EnsembleGenerator in your document. Could you give an example of how EnsembleGenerator works? What is the meaning of each parameter?

lihuiliullh

I created a KG and intended to split them into train/val/test without negative triples. I saved my KG as a multidigraph (networkx) and set resample_negatives=False. However, the splitting graphs still...

SRL94

Hi! The explanation of `forward_op` is a bit confusing and I think that it has some typos. It is not clear what this means: Given a dictionary input x, it...

emmapass