Fabrizio Boncoraglio
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Fabrizio Boncoraglio has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Davide Ghio
École Polytechnique Fédérale de Lausanne
1 shared publication - Jean-François de Kemmeter
Royal Military Academy
1 shared publication - Lenka Zdeborová
École Polytechnique Fédérale de Lausanne (EPFL)
1 shared publication - Luca Gallo
Department of Network and Data Science, Central European University, Vienna, Austria
1 shared publication - Timoteo Carletti
Namur Institute for Complex Systems
1 shared publication - Vito Latora
School of Mathematical Sciences, Queen Mary University of London
1 shared publication
Latest Publications
- 7 January 2026
- Published by American Physical Society (APS) in Physical Review E
- Vol. 113 (1) , 015301
Inference in spreading processes with neural-network priors
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.
- 7 January 2026
- Published by American Physical Society (APS) in Physical Review E
- Vol. 113 (1) , 015301
Inference in spreading processes with neural-network priors
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.
- 17 May 2024
- Published by World Scientific Pub Co Pte Ltd in Advances in Complex Systems
- Vol. 27 (04n05)
COMPLEX CONTAGION IN SOCIAL SYSTEMS WITH DISTRUST
Social systems are characterized by the presence of group interactions and by the existence of both trust and distrust relations. Although there is a wide literature on signed social networks, where positive signs associated to the links indicate trust, friendship, agreement, while negative signs represent distrust, antagonism, and disagreement, very little is known about the effect that signed interactions can have on the spreading of social behaviors when, not only pairwise, but also higher-order interactions are taken into account. In this paper, we introduce a model of complex contagion on signed simplicial complexes, and we investigate the role played by trust and distrust on the dynamics of a social contagion process, where exposure to multiple sources is needed for the contagion to occur. The presence of higher-order signed structures in our model naturally induces new infection and recovery mechanisms, thus increasing the richness of the contagion dynamics. Through numerical simulations and analytical results in the mean-field approximation, we show how distrust determines the way the system moves from a state where no individuals adopt the social behavior, to a state where a finite fraction of the population actively spreads it. Interestingly, we observe that the fraction of spreading individuals displays a non-monotonic dependence with respect to the average number of connections between individuals. We then investigate how social balance affects social contagion, finding that balanced triads have an ambivalent impact on the spreading process, either promoting or impeding contagion based on the relative abundance of fully trusted relations. Our results shed light on the nontrivial effect of trust on the spreading of social behaviors in systems with group interactions, paving the way to further investigations of spreading phenomena in structured populations.
- 17 May 2024
- Published by World Scientific Pub Co Pte Ltd in Advances in Complex Systems
- Vol. 27 (04n05)
COMPLEX CONTAGION IN SOCIAL SYSTEMS WITH DISTRUST
Social systems are characterized by the presence of group interactions and by the existence of both trust and distrust relations. Although there is a wide literature on signed social networks, where positive signs associated to the links indicate trust, friendship, agreement, while negative signs represent distrust, antagonism, and disagreement, very little is known about the effect that signed interactions can have on the spreading of social behaviors when, not only pairwise, but also higher-order interactions are taken into account. In this paper, we introduce a model of complex contagion on signed simplicial complexes, and we investigate the role played by trust and distrust on the dynamics of a social contagion process, where exposure to multiple sources is needed for the contagion to occur. The presence of higher-order signed structures in our model naturally induces new infection and recovery mechanisms, thus increasing the richness of the contagion dynamics. Through numerical simulations and analytical results in the mean-field approximation, we show how distrust determines the way the system moves from a state where no individuals adopt the social behavior, to a state where a finite fraction of the population actively spreads it. Interestingly, we observe that the fraction of spreading individuals displays a non-monotonic dependence with respect to the average number of connections between individuals. We then investigate how social balance affects social contagion, finding that balanced triads have an ambivalent impact on the spreading process, either promoting or impeding contagion based on the relative abundance of fully trusted relations. Our results shed light on the nontrivial effect of trust on the spreading of social behaviors in systems with group interactions, paving the way to further investigations of spreading phenomena in structured populations.