Network Diffusions via Neural Mean-Field Dynamics

Abstract

We propose a novel learning framework based on neural mean-field dynamics for inference and estimation problems of diffusion on networks. Our new framework is derived from the Mori-Zwanzig formalism to obtain an exact evolution of the node infection probabilities, which renders a delay differential equation with memory integral approximated by learnable time convolution operators, resulting in a highly structured and interpretable RNN. Directly using cascade data, our framework can jointly learn the structure of the diffusion network and the evolution of infection probabilities, which are cornerstone to important downstream applications such as influence maximization. Connections between parameter learning and optimal control are also established. Empirical study shows that our approach is versatile and robust to variations of the underlying diffusion network models, and significantly outperform existing approaches in accuracy and efficiency on both synthetic and real-world data.

arXiv commentAccepted by NIPS2020, 21 pages, 5 figures

References in corpus (16)

• Semi-Supervised Classification with Graph Convolutional Networks
• Epidemic processes in complex networks
• Hierarchical structure and the prediction of missing links in networks
• Kronecker Graphs: An Approach to Modeling Networks
• Epidemic spreading in correlated complex networks
• DeepInf: Social Influence Prediction with Deep Learning
• Learning graphs from data: A signal representation perspective
• Connecting the Dots: Identifying Network Structure via Graph Signal Processing
• Uncovering the Temporal Dynamics of Diffusion Networks
• Sketch-based Influence Maximization and Computation: Scaling up with Guarantees
• A Priori Estimation Of Memory Effects In Coarse-Grained Nonlinear Systems Using The Mori-Zwanzig Formalism
• Multistage Campaigning in Social Networks
• Inferring Graphs from Cascades: A Sparse Recovery Framework
• Reconstructing parameters of spreading models from partial observations
• Scalable Influence Estimation Without Sampling
• Structure and Dynamics of Information Pathways in Online Media