Stochastic Graph Neural Networks

Abstract

Graph neural networks (GNNs) model nonlinear representations in graph data with applications in distributed agent coordination, control, and planning among others. Current GNN architectures assume ideal scenarios and ignore link fluctuations that occur due to environment, human factors, or external attacks. In these situations, the GNN fails to address its distributed task if the topological randomness is not considered accordingly. To overcome this issue, we put forth the stochastic graph neural network (SGNN) model: a GNN where the distributed graph convolution module accounts for the random network changes. Since stochasticity brings in a new learning paradigm, we conduct a statistical analysis on the SGNN output variance to identify conditions the learned filters should satisfy for achieving robust transference to perturbed scenarios, ultimately revealing the explicit impact of random link losses. We further develop a stochastic gradient descent (SGD) based learning process for the SGNN and derive conditions on the learning rate under which this learning process converges to a stationary point. Numerical results corroborate our theoretical findings and compare the benefits of SGNN robust transference with a conventional GNN that ignores graph perturbations during learning.

References in corpus (17)

• A Comprehensive Survey on Graph Neural Networks
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Neural Message Passing for Quantum Chemistry
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Discrete Signal Processing on Graphs
• Session-based Recommendation with Graph Neural Networks
• Deep Convolutional Networks on Graph-Structured Data
• Graph Convolutional Matrix Completion
• DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
• How Powerful are Graph Neural Networks?
• Convolutional Neural Network Architectures for Signals Supported on Graphs
• Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems
• Autoregressive Moving Average Graph Filtering
• Stability Properties of Graph Neural Networks
• Graphs, Convolutions, and Neural Networks: From Graph Filters to Graph Neural Networks
• Filtering Random Graph Processes Over Random Time-Varying Graphs
• Controllability of Bandlimited Graph Processes Over Random Time Varying Graphs

Cited by in corpus (2)

• Wide and Deep Graph Neural Network with Distributed Online Learning
• Learning Stochastic Graph Neural Networks with Constrained Variance