I have a graph convolution model built and wanted to implement a custom unsupervised loss function like the one shown in below picture:
Loss Function
Where yv is the learned embedding of a node v and rand denotes random sampling operation over all the nodes
I am new to Pytorch so not sure if this is already implemented. Any help will be sincerely appreciated.
Since I am new to Pytorch, not sure where to get started with implementing a custom loss function
New contributor
Arun Kumar is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.