Confusing code - Githubissues

shenweichen / GraphEmbedding

Implementation and experiments of graph embedding algorithms.

MIT License

3.68k stars 995 forks source link

Confusing code #37

Open hxtruong6 opened 4 years ago

hxtruong6 commented 4 years ago

Hi, I am trying to re-implement SDNE code but I got stuck when reading code. Could you explain for me these below lines: -https://github.com/shenweichen/GraphEmbedding/blob/7de7a09aa17831ef480beb4658b2c76ed6f9a22f/ge/models/sdne.py#L162 : what is meaning of get('weight',1). Why does it has 1 value here?

https://github.com/shenweichen/GraphEmbedding/blob/7de7a09aa17831ef480beb4658b2c76ed6f9a22f/ge/models/sdne.py#L169 : what is A_ and its purpose?
https://github.com/shenweichen/GraphEmbedding/blob/7de7a09aa17831ef480beb4658b2c76ed6f9a22f/ge/models/sdne.py#L172 : how does this line create a diagonal matrix? I suppose this is a formula.
https://github.com/shenweichen/GraphEmbedding/blob/7de7a09aa17831ef480beb4658b2c76ed6f9a22f/ge/models/sdne.py#L125 : this is code to get L[i:j, :] for a mini batch to train. But what is meaning of L[index][:, index].todense() with index = [i:j]
https://github.com/shenweichen/GraphEmbedding/blob/7de7a09aa17831ef480beb4658b2c76ed6f9a22f/ge/models/sdne.py#L46 : where place do you pass parameterss for Loss function? How to know L = y_true and Y = y_pred?

Thank your helping!