JuliaDecisionFocusedLearning / InferOpt.jl

Combinatorial optimization layers for machine learning pipelines
https://juliadecisionfocusedlearning.github.io/InferOpt.jl/
MIT License
115 stars 4 forks source link

differentiable graph creation #23

Closed jakubMitura14 closed 2 years ago

jakubMitura14 commented 2 years ago

Hello I have a task to create a graph from the output of the convolutional neural network that then will be used in graph neural network. I have a cost function that can tell wheather graph was well created. My main problem is that graph by its nature is discrete hence constructing graph creation algorithm in a way that will enable back propagation is problematic (as you see in my architecture gradients need to pass from graph neural networks to CNN)

Can it be potentially possible to use your package for differentiable graph creation from 3D array?

rejuvyesh commented 2 years ago

Depending on how the graph edge is represented, a gumble softmax is the usual thing to do in that case to differentiate through your graph edge predictions.

jakubMitura14 commented 2 years ago

thank You !! I will investigate this path!