GraphSage unsupervised loss function

The paper “Inductive Representation Learning on Large Graphs (Graphsage)” has an unsupervised loss function based on random walks (sec 3.2 and image below) that is similar to deepwalk and node2vec, I couldn’t find it anywhere.

Is there an implementation or a plan to implement this loss function in pytorch?

For instance, for a binary cross entropy loss function you just have to use : torch.nn.functional.binary_cross_entropy.
Is there a similar function for the loss of the authors of the section 3.2 ?

Thank you all !

I think your Question is related to this issue:

Short this is an Example: pytorch_geometric/examples/graph_sage_unsup_ppi.py at master · pyg-team/pytorch_geometric · GitHub