PDSL: Propagation Dynamics Aware Framework for Source Localization

2026-05-05

AI Summary

This work addresses the challenge of source localization, where uncertainty between observations and the true source is difficult to quantify, primarily due to insufficient modeling of the inherent stochasticity in diffusion processes. To overcome this limitation, the authors propose a novel framework that integrates deep generative models with propagation dynamics, explicitly incorporating diffusion randomness into source localization for the first time. The approach employs graph neural ordinary differential equations to model continuous-time dynamics without requiring predefined mechanisms and introduces a data chunk matching strategy to enhance the reliability of source distribution estimation. Extensive experiments demonstrate that the proposed method significantly outperforms existing approaches on both synthetic and real-world propagation datasets, confirming its effectiveness and robustness.

Abstract

Source localization is a representative inverse inference task in information propagation, aiming to identify the source node or node set that triggers the propagation results based on the observed information. A primary challenge is quantifying the inherent uncertainty between observed outcomes and potential sources. Although deep generative models have partially mitigated this issue, most existing approaches primarily focus on uncertainty induced by network topology, attempting to learn a direct mapping from propagation outcomes to sources based on network structure, while overlooking the additional uncertainty stemming from the highly stochastic nature of the propagation process. To address this limitation, we propose a Propagation Dynamics aware framework for Source Localization (PDSL), a novel method that integrates a deep generative model with propagation dynamics to approximate the source distribution and explicitly mitigate uncertainty arising from diffusion stochasticity. Moreover, we employ Graph Neural Ordinary Differential Equations to model the continuous dynamics of diffusion processes without relying on a predefined diffusion mechanism. Additionally, a matching mechanism is designed to extract relevant data blocks that enhance source generation reliability. Comprehensive experiments on both synthetic and real-world diffusion datasets demonstrate the superior performance of the proposed framework across diverse application scenarios.

Problem

• source localization
• information propagation
• uncertainty quantification
• diffusion stochasticity
• inverse inference

Innovation

• Propagation Dynamics
• Source Localization
• Graph Neural ODEs
• Deep Generative Model
• Diffusion Stochasticity