Learning epidemic threshold in complex networks by Convolutional Neural Network

Predicting epidemic threshold in complex networks by graph neural network

To achieve precision in predicting an epidemic threshold in complex networks, we have developed a novel threshold graph neural network (TGNN) that takes into account both the network topology and the spreading dynamical process, which together contribute to the epidemic threshold. The proposed TGNN could effectively and accurately predict the epidemic threshold in homogeneous networks, characterized by a small variance in the degree distribution, such as Erdős-Rényi random networks. Usability has also been validated when the range of the effective spreading rate is altered. Furthermore, extensive experiments in ER networks and scale-free networks validate the adaptability of the TGNN to different network topologies without the necessity for retaining. The adaptability of the TGNN is further validated in real-world networks.

Neural-SEIR: A flexible data-driven framework for precise prediction of epidemic disease

Accurately modeling and predicting epidemic diseases is crucial to prevent disease transmission and reduce mortality. Due to various unpredictable factors, including population migration, vaccination, control efforts, and seasonal fluctuations, traditional epidemic models that rely on prior knowledge of virus transmission mechanisms may not be sufficient to forecast complex epidemics like coronavirus disease 2019(COVID-19). The application of traditional epidemiological models such as susceptible-exposed-infectious-recovered (SEIR) may face difficulties in accurately predicting such complex epidemics. Data-driven prediction approaches lack the ability to generalize and exhibit low accuracy on small datasets due to their reliance on large amounts of data without incorporating prior knowledge. To overcome this limitation, we introduce a flexible ensemble data-driven framework (Neural-SEIR) that "neuralizes" the SEIR model by approximating the core parameters through neural networks while preserving the propagation structure of SEIR. Neural-SEIR employs long short-term memory (LSTM) neural network to capture complex correlation features, exponential smoothing (ES) to model seasonal information, and prior knowledge from SEIR. By incorporating SEIR parameters into the neural network structure, Neural-SEIR leverages prior knowledge while updating parameters with real-world data. Our experimental results demonstrate that Neural-SEIR outperforms traditional machine learning and epidemiological models, achieving high prediction accuracy and efficiency in forecasting epidemic diseases.

A Two-Phase Feature Selection Method for Identifying Influential Spreaders of Disease Epidemics in Complex Networks

Network epidemiology plays a fundamental role in understanding the relationship between network structure and epidemic dynamics, among which identifying influential spreaders is especially important. Most previous studies aim to propose a centrality measure based on network topology to reflect the influence of spreaders, which manifest limited universality. Machine learning enhances the identification of influential spreaders by combining multiple centralities. However, several centrality measures utilized in machine learning methods, such as closeness centrality, exhibit high computational complexity when confronted with large network sizes. Here, we propose a two-phase feature selection method for identifying influential spreaders with a reduced feature dimension. Depending on the definition of influential spreaders, we obtain the optimal feature combination for different synthetic networks. Our results demonstrate that when the datasets are mildly or moderately imbalanced, for Barabasi-Albert (BA) scale-free networks, the centralities' combination with the two-hop neighborhood is fundamental, and for Erdős-Rényi (ER) random graphs, the centralities' combination with the degree centrality is essential. Meanwhile, for Watts-Strogatz (WS) small world networks, feature selection is unnecessary. We also conduct experiments on real-world networks, and the features selected display a high similarity with synthetic networks. Our method provides a new path for identifying superspreaders for the control of epidemics.

A sampling-guided unsupervised learning method to capture percolation in complex networks

The use of machine learning methods in classical and quantum systems has led to novel techniques to classify ordered and disordered phases, as well as uncover transition points in critical phenomena. Efforts to extend these methods to dynamical processes in complex networks is a field of active research. Network-percolation, a measure of resilience and robustness to structural failures, as well as a proxy for spreading processes, has numerous applications in social, technological, and infrastructural systems. A particular challenge is to identify the existence of a percolation cluster in a network in the face of noisy data. Here, we consider bond-percolation, and introduce a sampling approach that leverages the core-periphery structure of such networks at a microscopic scale, using onion decomposition, a refined version of the k-core. By selecting subsets of nodes in a particular layer of the onion spectrum that follow similar trajectories in the percolation process, percolating phases can be distinguished from non-percolating ones through an unsupervised clustering method. Accuracy in the initial step is essential for extracting samples with information-rich content, that are subsequently used to predict the critical transition point through the confusion scheme, a recently introduced learning method. The method circumvents the difficulty of missing data or noisy measurements, as it allows for sampling nodes from both the core and periphery, as well as intermediate layers. We validate the effectiveness of our sampling strategy on a spectrum of synthetic network topologies, as well as on two real-word case studies: the integration time of the US domestic airport network, and the identification of the epidemic cluster of COVID-19 outbreaks in three major US states. The method proposed here allows for identifying phase transitions in empirical time-varying networks.

Texture classification based on image (natural and horizontal) visibility graph constructing methods

Texture classification is widely used in image analysis and some other related fields. In this paper, we designed a texture classification algorithm, named by TCIVG (Texture Classification based on Image Visibility Graph), based on a newly proposed image visibility graph network constructing method by Lacasa et al. By using TCIVG on a Brodatz texture image database, the whole procedure is illustrated. First, each texture image in the image database was transformed to an associated image natural visibility graph network and an image horizontal visibility graph network. Then, the degree distribution measure [P(k)] was extracted as a key characteristic parameter to different classifiers. Numerical experiments show that for artificial texture images, a 100% classification accuracy can be obtained by means of a quadratic discriminant based on natural TCIVG. For natural texture images, 94.80% classification accuracy can be obtained by a linear SVM (Support Vector Machine) based on horizontal TCIVG. Our results are better than that reported in some existing literature studies based on the same image database.