jeongwhanchoi / BracketGraphs

Code accompanying "Reversible and irreversible bracket-based dynamics for deep graph neural networks" NeurIPS 2023 paper.

Structure-preserving bracket-based GNNs

This code reproduces results from the paper:

A. Gruber, K. Lee, N. Trask, "Reversible and irreversible bracket-based dynamics for deep graph neural networks", NeurIPS 2023.

Running the code

The file "parameters.md" provides explicit commands that can be run to generate our results.

Dependencies:

• NumPy
• PyTorch
• PyTorch Geometric