Grid Search for GNNs #1070
Labels
class::feature
A feature to be implemented for some part of the software
class::improvement
Cleanup that doesn't affect functionality
model::ode
This issue concerns any kind of ODE-based model.
Enhancement description
In order to find the best GNN architecture suitable for our task, we conduct a grid serach for foru different model types.
Tha parameters that are varied are the model depth (number of layers) and the model width (number of units per layer).
This code is important to ensure replicability of the results of the master thesis.
The training data is generated by the MEmilio graph-ODE model and then split into input and label for the model as implemented in #1057.
Checklist
The text was updated successfully, but these errors were encountered: