![[Maison.png]](../../images/Maison.png)
Back to Home| Abstract A graph neural network with three bipartite graphs based on a topology of a network, Gp,l connecting paths in a network to their links, Gl,n connecting links to nodes defining the links, and Gp,n connecting paths to nodes, wherein each vertex of the bipartite graphs has a hidden state to be passed to its neighbours during iterated message passing convolutions, the graph neural network is injected network parameters and load are injected into the above graphs. A network characteristic combines the resulting outputs using a fully connected layer. |
Copies / Update: Please contact me by email if you wish to obtain a copy of a paper that is not available on line.
Back to Home