GATNE icon indicating copy to clipboard operation
GATNE copied to clipboard

How features are generated?

Open geo47 opened this issue 3 years ago • 5 comments

Hello,

Could you please guide how you generated feature embeddings for each node?

More specifically, I guess the feature embedding represents the attribute features of the node. If we use Node2Vec for embedding it only gives the node embedding, however using GraphSAGE we can obtain embedding with node and attributes.

Thanks

geo47 avatar Aug 05 '21 06:08 geo47

Hi @geo47,

What do feature embeddings mean? Actually, our method is similar to unsupervised GraphSAGE to generate node embeddings with both structural and attribute information. But we mainly focus on the multiplex heterogeneous scenarios.

cenyk1230 avatar Aug 10 '21 04:08 cenyk1230

Hi @cenyk1230 ,

Thanks for the reply.

By feature embedding, I mean how you generate the feature embedding in the feature.txt file.

Like, if I want to generate it on my own custom data, how can I do that as I need to generate node embeddings with both structural and attribute information.

Thanks.

geo47 avatar Aug 10 '21 06:08 geo47

Hi @geo47,

It depends on your dataset. Does your dataset contain node attributes, either continuous or discrete attributes? You can transform the discrete attributes into one-hot encodings and concatenate them with continuous attributes as initial node features.

cenyk1230 avatar Aug 10 '21 13:08 cenyk1230

Yes, I have discrete node attributes. Can you please provide any reference to generate a one-hot encoding representation of node with attributes to generate feature.txt file?

Thanks

geo47 avatar Aug 12 '21 04:08 geo47

Hello, Can you please provide any reference to generate a one-hot encoding representation of node with attributes to generate feature.txt file? Do you have an answer to this question?

Thanks

ynyunbest avatar Oct 15 '21 08:10 ynyunbest