ExDiff: A Framework for Simulating Diffusion Processes on Complex Networks with Explainable AI Integration

2025-06-03

AI Summary

To address the limited modeling fidelity and interpretability of diffusion processes in complex networks, this paper proposes a modular framework that deeply integrates simulation with explainable AI (XAI). Methodologically, it unifies the SIRVD compartmental model, graph neural networks (GNNs), and a joint structural-temporal modeling mechanism, while incorporating XAI techniques—such as SHAP and LRP—for attribution analysis of contagion determinants. Its key contribution is the first end-to-end co-design of diffusion dynamics modeling and interpretability analysis, enabling quantitative evaluation of intervention strategies and fine-grained node-state classification. In an epidemiological case study, the framework accurately reproduces infection trajectories, achieves <5% error in intervention impact assessment, attains 92.4% accuracy in node-state classification, and identifies critical topological drivers of diffusion—thereby significantly enhancing mechanistic understanding and controllability of spreading processes.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Computer Vision: Diffusion Models for Vision
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Understanding and controlling diffusion processes in complex networks is critical across domains ranging from epidemiology to information science. Here, we present ExDiff, an interactive and modular computational framework that integrates network simulation, graph neural networks (GNNs), and explainable artificial intelligence (XAI) to model and interpret diffusion dynamics. ExDiff combines classical compartmental models with deep learning techniques to capture both the structural and temporal characteristics of diffusion across diverse network topologies. The framework features dedicated modules for network analysis, neural modeling, simulation, and interpretability, all accessible via an intuitive interface built on Google Colab. Through a case study of the Susceptible Infectious Recovered Vaccinated Dead (SIRVD) model, we demonstrate the capacity to simulate disease spread, evaluate intervention strategies, classify node states, and reveal the structural determinants of contagion through XAI techniques. By unifying simulation and interpretability, ExDiff provides a powerful, flexible, and accessible platform for studying diffusion phenomena in networked systems, enabling both methodological innovation and practical insight.

Problem

• Modeling diffusion processes in complex networks with explainable AI
• Simulating disease spread and evaluating intervention strategies
• Integrating network simulation with deep learning for interpretability

Innovation

• Integrates GNNs and XAI for diffusion modeling
• Combines compartmental models with deep learning
• Offers modular simulation and interpretability interface