Graph Neural Aggregation-diffusion with Metastability

arXiv:2403.20221v1 Announce Type: new
Abstract: Continuous graph neural models based on differential equations have expanded the architecture of graph neural networks (GNNs). Due to the connection between graph diffusion and message passing, diffusion-based models have been widely studied. However, diffusion naturally drives the system towards an equilibrium state, leading to issues like over-smoothing. To this end, we propose GRADE inspired by graph aggregation-diffusion equations, which includes the delicate balance between nonlinear diffusion and aggregation induced by interaction potentials. The node …

abstract aggregation architecture arxiv continuous cs.ai cs.lg differential diffusion equilibrium gnns graph graph neural networks however networks neural networks state type