Graph-Coupled Oscillator Networks. (arXiv:2202.02296v2 [cs.LG] UPDATED)

We propose Graph-Coupled Oscillator Networks (GraphCON), a novel framework
for deep learning on graphs. It is based on discretizations of a second-order
system of ordinary differential equations (ODEs), which model a network of
nonlinear controlled and damped oscillators, coupled via the adjacency
structure of the underlying graph. The flexibility of our framework permits any
basic GNN layer (e.g. convolutional or attentional) as the coupling function,
from which a multi-layer deep neural network is built up via the dynamics of
the …

arxiv graph lg networks