- Physical Review Journals
All JournalsPhysics Magazine
Access Provided by Xinjiang University

Physical Review E

Export citation

Export citation

Choose format for download:

Download Citation
  • Editors' Suggestion
  • Access by Xinjiang University

Inference in spreading processes with neural-network priors

Davide Ghio1,*, Fabrizio Boncoraglio2, and Lenka Zdeborová2

  • *Contact author: davide.ghio98@gmail.com
PDF

Phys. Rev. E 113, 015301 – Published 7 January, 2026

DOI: https://doi.org/10.1103/8mww-brdk

Abstract

Stochastic processes on graphs are a powerful tool for modeling complex dynamical systems such as epidemics. A recent line of work focused on the inference problem where one aims to estimate the state of every node at every time, starting from partial observation of a subset of nodes at a subset of times. In these works, the initial state of the process was assumed to be random independent and identically distributed over nodes. Such an assumption may not be realistic in practice, where one may have access to a set of covariate variables for every node that influences the initial state of the system. In this work, we will assume that the initial state of a node is an unknown function of such covariate variables. Given that functions can be represented by neural networks, we will study a model where the initial state is given by a simple neural network—notably the single-layer perceptron acting on the known nodewise covariate variables. Within a Bayesian framework, we study how such neural-network prior information enhances the recovery of initial states and spreading trajectories. We derive a hybrid belief propagation and approximate message passing (BP-AMP) algorithm that handles both the spreading dynamics and the information included in the node covariates, and we assess its performance against the estimators that use only the spreading information or use only the information from the covariate variables. We show that in some regimes, the model can exhibit first-order phase transitions when using a Rademacher distribution for the neural-network weights. These transitions create a statistical-to-computational gap where even the BP-AMP algorithm, despite the theoretical possibility of perfect recovery, fails to achieve it.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (48)

  1. A. Vespignani, Modelling dynamical processes in complex socio-technical systems, Nat. Phys. 8, 32 (2012).
  2. R. Pastor-Satorras, C. Castellano, P. Van Mieghem, and A. Vespignani, Epidemic processes in complex networks, Rev. Mod. Phys. 87, 925 (2015).
  3. M. J. Keeling and K. T. D. Eames, Networks and epidemic models, J. R. Soc. Interface 2, 295 (2005).
  4. G. Karlebach and R. Shamir, Modelling and analysis of gene regulatory networks, Nat. Rev. Mol. Cell Biol. 9, 770 (2008).
  5. D.-U. Hwang, Complex networks: Structure and dynamics, Phys. Rep. 424, 175 (2006).
  6. A. Y. Lokhov, M. Mézard, H. Ohta, and L. Zdeborová, Inferring the origin of an epidemic with a dynamic message-passing algorithm, Phys. Rev. E 90, 012801 (2014).
  7. F. Altarelli, A. Braunstein, L. Dall'Asta, A. Lage-Castellanos, and R. Zecchina, Bayesian inference of epidemics on networks via belief propagation, Phys. Rev. Lett. 112, 118701 (2014).
  8. B. Aubin, B. Loureiro, A. Maillard, F. Krzakala, and L. Zdeborová, The spiked matrix model with generative priors, in Advances in Neural Information Processing Systems 32 (Curran Associates, Inc., 2019), pp. 8364–837.
  9. B. Aubin, B. Loureiro, A. Baker, F. Krzakala, and L. Zdeborová, Exact asymptotics for phase retrieval and compressed sensing with random generative priors, in Proceedings of The First Mathematical and Scientific Machine Learning Conference, Proceedings of Machine Learning Research, edited by J. Lu and R. Ward (PMLR, 2020), Vol. 107, pp. 55–73.
  10. M. Mezard and A. Montanari, Information, Physics, and Computation (Oxford University Press, New York, 2009).
  11. L. Zdeborová and F. Krzakala, Statistical physics of inference: Thresholds and algorithms, Adv. Phys. 65, 453 (2016).
  12. J. Barbier, F. Krzakala, N. Macris, L. Miolane, and L. Zdeborová, Optimal errors and phase transitions in high-dimensional generalized linear models, Proc. Natl. Acad. Sci. USA 116, 5451 (2019).
  13. A. Manoel, F. Krzakala, M. Mézard, and L. Zdeborová, Multi-layer generalized linear estimation, in 2017 IEEE International Symposium on Information Theory (ISIT) (IEEE, New York, 2017), pp. 2098–2102.
  14. O. Duranthon and L. Zdeborová, Neural-prior stochastic block model, Mach. Learn.: Sci. Technol. 4, 035017 (2023).
  15. M. E. J. Newman, The structure and function of complex networks, SIAM Rev. 45, 167 (2003).
  16. I. Z. Kiss, J. C. Miller, P. L. Simon, Mathematics of Epidemics on Networks From Exact to Approximate Models, Interdisciplinary Applied Mathematics Vol. 46 (Springer, Cham, 2017).
  17. W. O. Kermack, A. G. McKendrick, and G. T. Walker, Contributions to the mathematical theory of epidemics. II. The problem of endemicity, Proc. R. Soc. London, Ser. A 138, 55 (1932).
  18. P. E. Paré, C. L. Beck, and T. Başar, Modeling, estimation, and analysis of epidemics over networks: An overview, Annu. Rev. Control 50, 345 (2020).
  19. D. Shah and T. Zaman, Detecting sources of computer viruses in networks: Theory and experiment, ACM SIGMETRICS Perform. Eval. Rev. 38, 203 (2010).
  20. D. Shah and T. Zaman, Rumors in a network: Who's the culprit? IEEE Trans. Inf. Theor. 57, 5163 (2011).
  21. N. Antulov-Fantulin, A. Lancic, H. Stefancic, M. Sikic, and T. Smuc, Statistical inference framework for source detection of contagion processes on arbitrary network structures, in Proceedings of the 2014 IEEE Eighth International Conference on Self-Adaptive and Self-Organizing Systems Workshops (IEEE, 2014), pp. 78–83.
  22. W. Dong, W. Zhang, and C. W. Tan, Rooting out the rumor culprit from suspects, in Proceedings of the 2013 IEEE International Symposium on Information Theory (IEEE, New York, 2013), pp. 2671–2675.
  23. P. C. Pinto, P. Thiran, and M. Vetterli, Locating the source of diffusion in large-scale networks, Phys. Rev. Lett. 109, 068702 (2012).
  24. B. Karrer and M. E. J. Newman, Message passing approach for general epidemic models, Phys. Rev. E 82, 016101 (2010).
  25. F. Altarelli, A. Braunstein, L. Dall'Asta, A. Ingrosso, and R. Zecchina, The patient-zero problem with noisy observations, J. Stat. Mech. (2014) P10016.
  26. A. Y. Lokhov, Reconstructing parameters of spreading models from partial observations, in Advances in Neural Information Processing Systems 29 (Curran Associates, Inc., 2016), pp. 3459–3467.
  27. A. Baker, I. Biazzo, A. Braunstein, G. Catania, L. Dall'Asta, A. Ingrosso, F. Krzakala, F. Mazza, M. Mézard, A. P. Muntoni, et al., Epidemic mitigation by statistical inference from contact tracing data, Proc. Natl. Acad. Sci. USA 118, e2106548118 (2021).
  28. M. Gabrié, A. Manoel, C. Luneau, J. Barbier, N. Macris, F. Krzakala, and L. Zdeborová, Entropy and mutual information in models of deep neural networks, J. Stat. Mech. (2019) 124014.
  29. E. Mallard and D. Saad, Inference by belief propagation in composite systems, Phys. Rev. E 78, 021107 (2008).
  30. J. Raymond and D. Saad, Equilibrium properties of disordered spin models with two-scale interactions, Phys. Rev. E 80, 031138 (2009).
  31. A. Braunstein, L. Budzynski, and M. Mariani, Statistical mechanics of inference in epidemic spreading, Phys. Rev. E 108, 064302 (2023).
  32. A. Braunstein, L. Budzynski, and M. Mariani, Evidence of replica symmetry breaking under the Nishimori conditions in epidemic inference on graphs, Phys. Rev. E 111, 064308 (2025).
  33. D. Ghio, Antoine L. M. Aragon, I. Biazzo, and L. Zdeborová, Bayes-optimal inference for spreading processes on random networks, Phys. Rev. E 108, 044308 (2023).
  34. W. Luo, W. P. Tay, and M. Leng, Identifying infection sources and regions in large networks, IEEE Trans. Signal Process. 61, 2850 (2013).
  35. K. Fan, A. E Aiello, and K. A Heller, Bayesian models for heterogeneous personalized health data, arXiv:1509.00110.
  36. E. Gardner, The space of interactions in neural network models, J. Phys. A: Math. Gen. 21, 257 (1988).
  37. E. Gardner and B. Derrida, Optimal storage properties of neural network models, J. Phys. A: Math. Gen. 21, 271 (1988).
  38. W. Krauth and M. Mézard, Storage capacity of memory networks with binary couplings, J. Phys. France 50, 3057 (1989).
  39. B. Spinelli, L. E. Celis, and P. Thiran, A general framework for sensor placement in source localization, IEEE Trans. Network Sci. Eng. 6, 86 (2017).
  40. H. Nishimori, Statistical Physics of Spin Glasses and Information Processing: An Introduction (Oxford University Press, Oxford, 2001).
  41. O. Duranthon and L. Zdeborová, Optimal inference in contextual stochastic block models, arXiv:2306.07948.
  42. J. S. Yedidia, W. T. Freeman, and Y. Weiss, Understanding belief propagation and its generalizations, in Exploring Artificial Intelligence in the New Millennium, edited by G. Lakemeyer and B. Nebel (Morgan Kaufmann, San Francisco, 2003), pp. 239–260.
  43. A. Coja-Oghlan, F. Krzakala, W. Perkins, and L. Zdeborová, Information-theoretic thresholds from the cavity method, Adv. Math. 333, 694 (2018).
  44. M. Celentano, A. Montanari, and Y. Wu, The estimation error of general first order methods, in Proceedings of the 33rd Conference on Learning Theory, Proceedings of Machine Learning Research (PMLR, 2020), Vol. 125, pp. 1078–1141.
  45. A. Montanari and A. S Wein, Equivalence of approximate message passing and low-degree polynomials in rank-one matrix estimation, Probab. Theory Relat. Fields (2024).
  46. E. Cornacchia, F. Mignacco, R. Veiga, C. Gerbelot, B. Loureiro, and L. Zdeborová, Learning curves for the multi-class teacher–student perceptron, Mach. Learn.: Sci. Technol. 4, 015019 (2023).
  47. D. Ghio, F. Boncoraglio, and L. Zdeborová, GitHub, 2025, https://github.com/IdePHICS/NeuralSpreadingInference.
  48. B. Bollobás, Random graphs, Modern Graph Theory (Springer, New York, 1998), pp. 215–252.

Outline

Information

Phys. Rev. E 113, 015301– Published 7 January, 2026
  • Received 11 September 2025
  • Accepted 1 December 2025
Crossmark - Check for updates button

©2026 American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation