Conformal Prediction for Multi-Source Detection on a Network

2025-11-12

AI Summary

Multi-source epidemic source localization—identifying the initial set of infected nodes from a single snapshot of node infection states—remains challenging, as existing methods either lack statistical guarantees or are constrained to specific diffusion models and network topologies. Method: We propose the first conformal prediction framework for this task with statistically guaranteed recall, requiring no assumptions about the underlying propagation model and applicable to arbitrary network structures and diffusion dynamics. Our core innovation is a novel scoring function that quantifies alignment between predicted infection probabilities and the true source set, enabling calibration of prediction sets to achieve user-specified recall levels. Results: Extensive experiments on diverse real-world and synthetic networks demonstrate that our method significantly outperforms state-of-the-art baselines, achieving high precision and computational scalability while strictly satisfying the prescribed coverage guarantee.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

Detecting the origin of information or infection spread in networks is a fundamental challenge with applications in misinformation tracking, epidemiology, and beyond. We study the multi-source detection problem: given snapshot observations of node infection status on a graph, estimate the set of source nodes that initiated the propagation. Existing methods either lack statistical guarantees or are limited to specific diffusion models and assumptions. We propose a novel conformal prediction framework that provides statistically valid recall guarantees for source set detection, independent of the underlying diffusion process or data distribution. Our approach introduces principled score functions to quantify the alignment between predicted probabilities and true sources, and leverages a calibration set to construct prediction sets with user-specified recall and coverage levels. The method is applicable to both single- and multi-source scenarios, supports general network diffusion dynamics, and is computationally efficient for large graphs. Empirical results demonstrate that our method achieves rigorous coverage with competitive accuracy, outperforming existing baselines in both reliability and scalability.The code is available online.

Problem

• Detecting multiple infection sources in network diffusion processes
• Providing statistical guarantees for source set recall coverage
• Developing model-agnostic framework for general network dynamics

Innovation

• Conformal prediction framework for source detection
• Principled score functions with calibration set
• Computationally efficient for large network graphs