NEDMP: Neural Enhanced Dynamic Message Passing
Fei Gao, Yan Zhang, Jiang Zhang

TL;DR
This paper introduces NEDMP, a hybrid neural network and message passing approach that improves the accuracy of predicting stochastic spreading processes on complex networks, especially those with many loops.
Contribution
The paper presents a novel hybrid model combining Graph Neural Networks with Dynamic Message Passing to enhance inference accuracy in complex networks.
Findings
NEDMP outperforms traditional DMP in various network structures.
The hybrid model generalizes better to unseen network conditions.
Training improves the accuracy of stochastic spreading predictions.
Abstract
Predicting stochastic spreading processes on complex networks is critical in epidemic control, opinion propagation, and viral marketing. We focus on the problem of inferring the time-dependent marginal probabilities of states for each node which collectively quantifies the spreading results. Dynamic Message Passing (DMP) has been developed as an efficient inference algorithm for several spreading models, and it is asymptotically exact on locally tree-like networks. However, DMP can struggle in diffusion networks with lots of local loops. We address this limitation by using Graph Neural Networks (GNN) to learn the dependency amongst messages implicitly. Specifically, we propose a hybrid model in which the GNN module runs jointly with DMP equations. The GNN module refines the aggregated messages in DMP iterations by learning from simulation data. We demonstrate numerically that after…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsOpinion Dynamics and Social Influence · Complex Network Analysis Techniques · Opportunistic and Delay-Tolerant Networks
