Finding Patient Zero: Learning Contagion Source with Graph Neural Networks

• URL: http://arxiv.org/abs/2006.11913v2
• Date: Sat, 27 Jun 2020 04:38:54 GMT
• Title: Finding Patient Zero: Learning Contagion Source with Graph Neural Networks
• Authors: Chintan Shah, Nima Dehmamy, Nicola Perra, Matteo Chinazzi, Albert-L\'aszl\'o Barab\'asi, Alessandro Vespignani, Rose Yu
• Abstract summary: Locating the source of an epidemic can provide critical insights into the infection's transmission course. Existing methods use graph-theoretic measures and expensive message-passing algorithms. We revisit this problem using graph neural networks (GNNs) to learn P0.
• Score: 67.3415507211942
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Locating the source of an epidemic, or patient zero (P0), can provide critical insights into the infection's transmission course and allow efficient resource allocation. Existing methods use graph-theoretic centrality measures and expensive message-passing algorithms, requiring knowledge of the underlying dynamics and its parameters. In this paper, we revisit this problem using graph neural networks (GNNs) to learn P0. We establish a theoretical limit for the identification of P0 in a class of epidemic models. We evaluate our method against different epidemic models on both synthetic and a real-world contact network considering a disease with history and characteristics of COVID-19. % We observe that GNNs can identify P0 close to the theoretical bound on accuracy, without explicit input of dynamics or its parameters. In addition, GNN is over 100 times faster than classic methods for inference on arbitrary graph topologies. Our theoretical bound also shows that the epidemic is like a ticking clock, emphasizing the importance of early contact-tracing. We find a maximum time after which accurate recovery of the source becomes impossible, regardless of the algorithm used.

Related papers

• Research on Early Warning Model of Cardiovascular Disease Based on Computer Deep Learning [5.761426161930679]
  This project intends to study a cardiovascular disease risk early warning model based on one-dimensional convolutional neural networks. The missing values of 13 physiological and symptom indicators such as patient age, blood glucose, cholesterol, and chest pain were filled and Z-score was standardized.
  arXiv  Detail & Related papers  (2024-06-13T07:04:22Z)
• Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning [91.29876772547348]
  Spiking neural networks (SNNs) are investigated as biologically inspired models of neural computation. This paper reveals that SNNs, when amalgamated with synaptic delay and temporal coding, are proficient in executing (knowledge) graph reasoning.
  arXiv  Detail & Related papers  (2024-05-27T05:53:30Z)
• Integrative Deep Learning Framework for Parkinson's Disease Early Detection using Gait Cycle Data Measured by Wearable Sensors: A CNN-GRU-GNN Approach [0.3222802562733786]
  We present a pioneering deep learning architecture tailored for the binary classification of subjects. Our model harnesses the power of 1D-Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and Graph Neural Network (GNN) layers. Our proposed model achieves exceptional performance metrics, boasting accuracy, precision, recall, and F1 score values of 99.51%, 99.57%, 99.71%, and 99.64%, respectively.
  arXiv  Detail & Related papers  (2024-04-09T15:19:13Z)
• Spatial Temporal Graph Convolution with Graph Structure Self-learning for Early MCI Detection [9.11430195887347]
  We propose a spatial temporal graph convolutional network with a novel graph structure self-learning mechanism for EMCI detection. Results on the Alzheimer's Disease Neuroimaging Initiative database show that our method outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-11-11T12:29:00Z)
• Influence Estimation and Maximization via Neural Mean-Field Dynamics [60.91291234832546]
  We propose a novel learning framework using neural mean-field (NMF) dynamics for inference and estimation problems. Our framework can simultaneously learn the structure of the diffusion network and the evolution of node infection probabilities.
  arXiv  Detail & Related papers  (2021-06-03T00:02:05Z)
• GKD: Semi-supervised Graph Knowledge Distillation for Graph-Independent Inference [41.348451615460796]
  We propose a novel semi-supervised approach named GKD based on knowledge distillation. We perform experiments on two public datasets for diagnosing Autism spectrum disorder, and Alzheimer's disease. According to these experiments, GKD outperforms the previous graph-based deep learning methods in terms of accuracy, AUC, and Macro F1.
  arXiv  Detail & Related papers  (2021-04-08T08:23:37Z)
• Examining COVID-19 Forecasting using Spatio-Temporal Graph Neural Networks [8.949096210063662]
  In this work, we examine a novel forecasting approach for COVID-19 case prediction that uses Graph Neural Networks and mobility data. We evaluate this approach on the US county level COVID-19 dataset, and demonstrate that the rich spatial and temporal information leveraged by the graph neural network allows the model to learn complex dynamics.
  arXiv  Detail & Related papers  (2020-07-06T23:11:38Z)
• Network Diffusions via Neural Mean-Field Dynamics [52.091487866968286]
  We propose a novel learning framework for inference and estimation problems of diffusion on networks. Our framework is derived from the Mori-Zwanzig formalism to obtain an exact evolution of the node infection probabilities. Our approach is versatile and robust to variations of the underlying diffusion network models.
  arXiv  Detail & Related papers  (2020-06-16T18:45:20Z)
• A Heterogeneous Graph with Factual, Temporal and Logical Knowledge for Question Answering Over Dynamic Contexts [81.4757750425247]
  We study question answering over a dynamic textual environment. We develop a graph neural network over the constructed graph, and train the model in an end-to-end manner.
  arXiv  Detail & Related papers  (2020-04-25T04:53:54Z)
• 1-D Convlutional Neural Networks for the Analysis of Pupil Size Variations in Scotopic Conditions [79.71065005161566]
  1-D convolutional neural network models are trained for classification of short-range sequences. Model provides prediction with high average accuracy on a hold out test set.
  arXiv  Detail & Related papers  (2020-02-06T17:25:37Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.