krzysztofrusek / net2vec

This repository is a collection of machine learning models for computer networks.

net2vec

This repository is a collection of machine learning models for computer networks. Currently, the following models are implemented:

1. Message Passing- vanilla Graph Neural Network
2. RouteNet - A new neural architecture designed for neural understanding of routing in the network.
3. Routing by Backprop - Differentiable surrogate for Dijkstra algorithm.

Queuing theory baselines used in many of the papers refered here are developed in a seperate reposity queuinx

If you decide to apply the concepts presented or base on the provided code, please do refer our related paper