Related papers: Inference in Spreading Processes with Neural-Network Priors

Inference in Spreading Processes with Neural-Network Priors

URL: http://arxiv.org/abs/2509.02073v1
Date: Tue, 02 Sep 2025 08:24:37 GMT
Title: Inference in Spreading Processes with Neural-Network Priors
Authors: Davide Ghio, Fabrizio Boncoraglio, Lenka Zdeborová,
Abstract summary: We study a model where the initial state of a node is given by a simple neural network.<n>Within a Bayesian framework, we study how such neural-network prior information enhances the recovery of initial states.
Score: 11.93069441086844
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Stochastic processes on graphs are a powerful tool for modelling 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 i.i.d. 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 influence 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 node-wise 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 either 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.

Related papers

A Spiking Neural Network Implementation of Gaussian Belief Propagation [3.05103886673788]
We investigate a distributed form of Bayesian inference, namely message passing on factor graphs.<n>We perform belief propagation by encoding messages that come into factor nodes as spike-based signals.<n>Three core linear operations, equality (branching), addition, and multiplication, are realized in networks of leaky integrate-and-fire models.
arXiv Detail & Related papers (2025-12-11T13:43:42Z)
Out-of-Distribution Detection using Neural Activation Prior [15.673290330356194]
Out-of-distribution detection (OOD) is a crucial technique for deploying machine learning models in the real world. We propose a simple yet effective Neural Activation Prior (NAP) for OOD detection. Our method achieves the state-of-the-art performance on CIFAR benchmark and ImageNet dataset.
arXiv Detail & Related papers (2024-02-28T08:45:07Z)
Backward and Forward Inference in Interacting Independent-Cascade Processes: A Scalable and Convergent Message-Passing Approach [1.1470070927586018]
We study the problems of estimating the past and future evolutions of two diffusion processes that spread concurrently on a network. We derive the exact joint probability of the initial state of the network and the observation-snapshot $mathcalO_n$.
arXiv Detail & Related papers (2023-10-29T20:03:38Z)
Continuous time recurrent neural networks: overview and application to forecasting blood glucose in the intensive care unit [56.801856519460465]
Continuous time autoregressive recurrent neural networks (CTRNNs) are a deep learning model that account for irregular observations. We demonstrate the application of these models to probabilistic forecasting of blood glucose in a critical care setting.
arXiv Detail & Related papers (2023-04-14T09:39:06Z)
Neural-prior stochastic block model [0.0]
We propose to model the communities as being determined by the node attributes rather than the opposite. We propose an algorithm, stemming from statistical physics, based on a combination of belief propagation and approximate message passing. The proposed model and algorithm can be used as a benchmark for both theory and algorithms.
arXiv Detail & Related papers (2023-03-17T14:14:54Z)
Invertible Neural Networks for Graph Prediction [22.140275054568985]
In this work, we address conditional generation using deep invertible neural networks. We adopt an end-to-end training approach since our objective is to address prediction and generation in the forward and backward processes at once.
arXiv Detail & Related papers (2022-06-02T17:28:33Z)
Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State [66.2457134675891]
Spiking neural networks (SNNs) are brain-inspired models that enable energy-efficient implementation on neuromorphic hardware. Most existing methods imitate the backpropagation framework and feedforward architectures for artificial neural networks. We propose a novel training method that does not rely on the exact reverse of the forward computation.
arXiv Detail & Related papers (2021-09-29T07:46:54Z)
Mitigating Performance Saturation in Neural Marked Point Processes: Architectures and Loss Functions [50.674773358075015]
We propose a simple graph-based network structure called GCHP, which utilizes only graph convolutional layers. We show that GCHP can significantly reduce training time and the likelihood ratio loss with interarrival time probability assumptions can greatly improve the model performance.
arXiv Detail & Related papers (2021-07-07T16:59:14Z)
And/or trade-off in artificial neurons: impact on adversarial robustness [91.3755431537592]
Presence of sufficient number of OR-like neurons in a network can lead to classification brittleness and increased vulnerability to adversarial attacks. We define AND-like neurons and propose measures to increase their proportion in the network. Experimental results on the MNIST dataset suggest that our approach holds promise as a direction for further exploration.
arXiv Detail & Related papers (2021-02-15T08:19:05Z)
Probabilistic Numeric Convolutional Neural Networks [80.42120128330411]
Continuous input signals like images and time series that are irregularly sampled or have missing values are challenging for existing deep learning methods. We propose Probabilistic Convolutional Neural Networks which represent features as Gaussian processes (GPs) We then define a convolutional layer as the evolution of a PDE defined on this GP, followed by a nonlinearity. In experiments we show that our approach yields a $3times$ reduction of error from the previous state of the art on the SuperPixel-MNIST dataset and competitive performance on the medical time2012 dataset PhysioNet.
arXiv Detail & Related papers (2020-10-21T10:08:21Z)
System Identification Through Lipschitz Regularized Deep Neural Networks [0.4297070083645048]
We use neural networks to learn governing equations from data. We reconstruct the right-hand side of a system of ODEs $dotx(t) = f(t, x(t))$ directly from observed uniformly time-sampled data.
arXiv Detail & Related papers (2020-09-07T17:52:51Z)
Revisiting Initialization of Neural Networks [72.24615341588846]
We propose a rigorous estimation of the global curvature of weights across layers by approximating and controlling the norm of their Hessian matrix. Our experiments on Word2Vec and the MNIST/CIFAR image classification tasks confirm that tracking the Hessian norm is a useful diagnostic tool.
arXiv Detail & Related papers (2020-04-20T18:12:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.