Graph neural networks estimate spreading rates in social networks
Gated Graph Neural Networks for Learning Hidden Independent Cascade Dynamics
Social and Information NetworksMachine Learning
Summary
Spreading information or diseases through social networks depends on how likely each person is to pass it on, but these probabilities are usually hidden. The authors study how to guess these hidden spreading rates using just noisy final data about who got infected or informed, without knowing exactly when it happened. They introduce a new technique that uses a special kind of graph-focused neural network combining observed symptoms with network structure to estimate each node’s spreading chance. Their approach works better on complex, realistic network shapes, while another existing method works best on simpler tree-like networks.
What this means in practice
- •For public health analysts: Estimate individual infection probabilities in disease spread using only noisy data about who was infected, improving epidemic response modeling.
- •For social media analysts: Infer how likely users are to share information by analyzing noisy outcomes in complex network structures, aiding targeted information campaigns.
Authors
Anubha Goel, Illia Oleksiienko, Mateusz Wilinski, Alexandros Iosifidis, Juho Kanniainen
Abstract
Information and infectious diseases spread through social networks, but the spreading probabilities driving them are hard to estimate without per-node activation times. Applications seldom supply these, and inference must instead proceed through indirect and noisy proxies for the terminal infection states. We study this inverse problem on a fixed, known graph under the Hidden Independent Cascade (HIC) model, with one spreading probability per node rather than a single global rate, so the number of unknowns scales with the number of nodes. Seed sets and observation parameters are known, while activation times and terminal infection states are latent, and the observed-data likelihood requires marginalizing over every spreading outcome. We propose a simulation-based amortized estimator that recovers the full node-level parameter vector without reconstructing individual latent cascades. Repeated seed-conditioned symptom observations are summarized as Symptom-Aware Cascade Features (SACF), which combine empirical symptom statistics with neighborhood and structural information. SACF are mapped to parameters by SAGE-HC, a permutation-equivariant gated graph neural network whose learned gates attenuate neighborhood messages corrupted by false positives and false negatives, and training on simulated HIC realizations yields a reusable inverse map. As a benchmark under the same hidden observations, we extend the Dynamic Message Passing learning framework to the HIC emission model. On synthetic and empirical graphs the two methods separate by topology. DMP is highly accurate on trees, whereas SAGE-HC is substantially better on heterogeneous, loopy graphs under noisy terminal symptoms.