.png){kind=icon}
.png){kind=icon}
Return
A charge-preserving method for solving graph neural diffusion networks
.png){kind=icon}
OA
AI
DOI：10.1016/j.cnsns.2024.108392.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The aim of this paper is to give a systematic mathematical interpretation of the diffusion problem on which Graph Neural Networks (GNNs) models are based. The starting point of our approach is a dissipative functional leading to dynamical equations which allows us to study the symmetries of the model. We provide a short review of graph theory and its relation with network sigma-models adapted to our analysis. We discuss the conserved charges and provide a charge-preserving numerical method for solving the dynamical equations. In any dynamical system and also in GRAph Neural Diffusion (GRAND), knowing the charge values and their conservation along the evolution flow could provide a way to understand how GNNs and other networks work with their learning capabilities.
Keywords:
Neural networks
Dynamical systems
Symmetries and conservation laws
Numerical methods for ODEs
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.8
Papers:
9.2K
Citations:
1.8W