24–28 Aug 2026
Kirchhoff Institute for Physics (KIP)
Europe/Berlin timezone

Hybrid GNN-Bayesian Models for Uncertainty-Aware Inference of Rare Events on Spatially Embedded Graphs

26 Aug 2026, 17:10
8m
HS1

HS1

Inference & Uncertainty 🔀 Inference & Uncertainty

Speaker

Federica Di Bartolomeo (Sapienza Università di Roma)

Description

We present a hybrid graph-based Bayesian framework for uncertainty-aware inference of rare events on spatially embedded networks.
Starting from a Multivariate Conditional Autoregressive Model (MCAR) in a hierarchical Bayesian architecture defined on the dual graph of a street network, events counts are described by Poisson likelihoods with structured graph effects, unstructured heterogeneity and node-level covariates. The approach was validated on georeferenced accidents data from Rome, where it enabled segment-level latent-risk estimation, crashes severity correlation modeling and calibrated posterior uncertainty.
We propose a physics-oriented extension combining this Bayesian graphical model with GNN-based amortized variational inference. A graph neural encoder learns local and non-local representations and parametrizes variational posteriors or Bayesian hyperparameters, without doing the optimization of the parameters for each observation. Meanwhile, the probabilistic layer preserves interpretable likelihoods, structured priors and uncertainty quantification. This hybrid formulation is scalable beyond MCMC and naturally suited to sparse, noisy, high-dimensional graphs. Potential applications include charged-particle tracking, vertexing, calorimeter clustering, pileup mitigation, jet anomaly detection, continuous gravitational-wave candidate clustering, astroparticle source association and multi-messenger event correlation.

Authors

Federica Di Bartolomeo (Sapienza Università di Roma) Gabriele Pignalberi (Sapienza Università di Roma and INFN) Stefano Giagu (Sapienza Università di Roma and Istituto Nazionale di Fisica Nucleare)

Presentation materials