
Wide and Deep Graph Neural Network with Distributed Online Learning
Graph neural networks (GNNs) are naturally distributed architectures for...
read it

Graph and graphon neural network stability
Graph neural networks (GNNs) are learning architectures that rely on kno...
read it

GraphTheta: A Distributed Graph Neural Network Learning System With Flexible Training Strategy
Graph neural networks (GNNs) have been demonstrated as a powerful tool f...
read it

ETA Prediction with Graph Neural Networks in Google Maps
Traveltime prediction constitutes a task of high importance in transpor...
read it

Stability of Graph Convolutional Neural Networks to Stochastic Perturbations
Graph convolutional neural networks (GCNNs) are nonlinear processing too...
read it

Graph neural induction of value iteration
Many reinforcement learning tasks can benefit from explicit planning bas...
read it

Implicit Graph Neural Networks
Graph Neural Networks (GNNs) are widely used deep learning models that l...
read it
Stochastic Graph Neural Networks
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.
READ FULL TEXT
Comments
There are no comments yet.