Bayesian Inductive Learner for Graph Resiliency under uncertainty

• URL: http://arxiv.org/abs/2012.15733v1
• Date: Sat, 26 Dec 2020 07:22:29 GMT
• Title: Bayesian Inductive Learner for Graph Resiliency under uncertainty
• Authors: Sai Munikoti and Balasubramaniam Natarajan
• Abstract summary: We propose a Bayesian graph neural network-based framework for identifying critical nodes in a large graph. The fidelity and the gain in computational complexity offered by the framework are illustrated.
• Score: 1.9254132307399257
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In the quest to improve efficiency, interdependence and complexity are becoming defining characteristics of modern engineered systems. With increasing vulnerability to cascading failures, it is imperative to understand and manage the risk and uncertainty associated with such engineered systems. Graph theory is a widely used framework for modeling interdependent systems and to evaluate their resilience to disruptions. Most existing methods in resilience analysis are based on an iterative approach that explores each node/link of a graph. These methods suffer from high computational complexity and the resulting analysis is network specific. Additionally, uncertainty associated with the underlying graphical model further limits the potential value of these traditional approaches. To overcome these challenges, we propose a Bayesian graph neural network-based framework for quickly identifying critical nodes in a large graph. while systematically incorporating uncertainties. Instead of utilizing the observed graph for training the model, a MAP estimate of the graph is computed based on the observed topology, and node target labels. Further, a Monte-Carlo (MC) dropout algorithm is incorporated to account for the epistemic uncertainty. The fidelity and the gain in computational complexity offered by the Bayesian framework are illustrated using simulation results.

Related papers

• Modularity aided consistent attributed graph clustering via coarsening [6.522020196906943]
  Graph clustering is an important unsupervised learning technique for partitioning graphs with attributes and detecting communities. We propose a loss function incorporating log-determinant, smoothness, and modularity components using a block majorization-minimization technique. Our algorithm seamlessly integrates graph neural networks (GNNs) and variational graph autoencoders (VGAEs) to learn enhanced node features and deliver exceptional clustering performance.
  arXiv  Detail & Related papers  (2024-07-09T10:42:19Z)
• Uncertainty-Aware Robust Learning on Noisy Graphs [16.66112191539017]
  This paper proposes a novel uncertainty-aware graph learning framework motivated by distributionally robust optimization. Specifically, we use a graph neural network-based encoder to embed the node features and find the optimal node embeddings. Such an uncertainty-aware learning process leads to improved node representations and a more robust graph predictive model.
  arXiv  Detail & Related papers  (2023-06-14T02:45:14Z)
• DEGREE: Decomposition Based Explanation For Graph Neural Networks [55.38873296761104]
  We propose DEGREE to provide a faithful explanation for GNN predictions. By decomposing the information generation and aggregation mechanism of GNNs, DEGREE allows tracking the contributions of specific components of the input graph to the final prediction. We also design a subgraph level interpretation algorithm to reveal complex interactions between graph nodes that are overlooked by previous methods.
  arXiv  Detail & Related papers  (2023-05-22T10:29:52Z)
• Dynamic Causal Explanation Based Diffusion-Variational Graph Neural Network for Spatio-temporal Forecasting [60.03169701753824]
  We propose a novel Dynamic Diffusion-al Graph Neural Network (DVGNN) fortemporal forecasting. The proposed DVGNN model outperforms state-of-the-art approaches and achieves outstanding Root Mean Squared Error result.
  arXiv  Detail & Related papers  (2023-05-16T11:38:19Z)
• Sparse Graph Learning from Spatiotemporal Time Series [16.427698929775023]
  We propose a graph learning framework that learns the relational dependencies as distributions over graphs. We show that the proposed solution can be used as a stand-alone graph identification procedure as well as a graph learning component of an end-to-end forecasting architecture.
  arXiv  Detail & Related papers  (2022-05-26T17:02:43Z)
• Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations [57.15855198512551]
  We propose a novel score-based generative model for graphs with a continuous-time framework. We show that our method is able to generate molecules that lie close to the training distribution yet do not violate the chemical valency rule.
  arXiv  Detail & Related papers  (2022-02-05T08:21:04Z)
• Bayesian Graph Contrastive Learning [55.36652660268726]
  We propose a novel perspective of graph contrastive learning methods showing random augmentations leads to encoders. Our proposed method represents each node by a distribution in the latent space in contrast to existing techniques which embed each node to a deterministic vector. We show a considerable improvement in performance compared to existing state-of-the-art methods on several benchmark datasets.
  arXiv  Detail & Related papers  (2021-12-15T01:45:32Z)
• Distributionally Robust Semi-Supervised Learning Over Graphs [68.29280230284712]
  Semi-supervised learning (SSL) over graph-structured data emerges in many network science applications. To efficiently manage learning over graphs, variants of graph neural networks (GNNs) have been developed recently. Despite their success in practice, most of existing methods are unable to handle graphs with uncertain nodal attributes. Challenges also arise due to distributional uncertainties associated with data acquired by noisy measurements. A distributionally robust learning framework is developed, where the objective is to train models that exhibit quantifiable robustness against perturbations.
  arXiv  Detail & Related papers  (2021-10-20T14:23:54Z)
• Graph neural network based approximation of Node Resiliency in complex networks [1.629817296011086]
  We propose a graph neural network (GNN) based framework for approximating node resilience in large complex networks. The proposed framework defines a GNN model that learns the node rank on a small representative subset of nodes. The scalability of the framework is demonstrated through the prediction of node ranks in real-world graphs.
  arXiv  Detail & Related papers  (2020-12-26T05:37:18Z)
• Structural Landmarking and Interaction Modelling: on Resolution Dilemmas in Graph Classification [50.83222170524406]
  We study the intrinsic difficulty in graph classification under the unified concept of resolution dilemmas'' We propose SLIM'', an inductive neural network model for Structural Landmarking and Interaction Modelling.
  arXiv  Detail & Related papers  (2020-06-29T01:01:42Z)

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.