Implicit graph neural network for deep graph transformation

Lei Zhang

doi:10.1007/s10115-025-02468-5

Implicit graph neural network for deep graph transformation

2025-05-26

0

PRE

AI

DOI：10.1007/s10115-025-02468-5

Original

Original request for help

Save

Abstract

En 中文

This study introduces a novel graph neural network architecture for the general problem of attributed graph transformation, where both the input and output are attributed graphs, and the evolution of the output graphs, including the attributes of nodes and edges, is governed by complex interactions that capture the intricate dependencies within the transformation process. Research in this area has been limited due to two key challenges: (1) the complexity of jointly modeling four types of atomic interactions, i.e., node-to-edge, node-to-node, edge-to-node, and edge-to-edge; and (2) the challenge of modeling dependencies between nodes and edges that span distant parts of the graph and develop through multiple iterative steps in the transformation process. To overcome these challenges, we present a scalable equilibrium model, NEC infinity\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$<^>{\infty }$$\end{document}, which incorporates both node-to-edge and edge-to-node message passing. Furthermore, we develop an efficient optimization algorithm based on the implicit function theorem [1] and provide a well-posedness analysis of NEC infinity\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$<^>{\infty }$$\end{document}. Experiments were conducted on four synthetic random graph datasets, four real-world datasets, and two synthetic dynamical system datasets, employing multiple evaluation metrics for node and edge prediction. The results show that NEC infinity\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$<^>{\infty }$$\end{document} consistently outperforms all baseline models, achieving up to a tenfold decrease in MSE on BA random graphs, edge prediction accuracy ranging from 94% to nearly 100% on synthetic datasets, and exceptional results in tasks involving molecular reactions and high-order brain networks, highlighting its strength in modeling complex graph transformations.

Keywords:

Node-edge co-evolution

Attributed graph transformation

Implicit equilibrium model

Graph neural networks

Implicit graph neural network for deep graph transformation

Abstract

Journal

Organization

Cited Papers