Learning Stochastic Graph Neural Networks with Constrained Variance

by   Zhan Gao, et al.

Stochastic graph neural networks (SGNNs) are information processing architectures that learn representations from data over random graphs. SGNNs are trained with respect to the expected performance, which comes with no guarantee about deviations of particular output realizations around the optimal expectation. To overcome this issue, we propose a variance-constrained optimization problem for SGNNs, balancing the expected performance and the stochastic deviation. An alternating primal-dual learning procedure is undertaken that solves the problem by updating the SGNN parameters with gradient descent and the dual variable with gradient ascent. To characterize the explicit effect of the variance-constrained learning, we conduct a theoretical analysis on the variance of the SGNN output and identify a trade-off between the stochastic robustness and the discrimination power. We further analyze the duality gap of the variance-constrained optimization problem and the converging behavior of the primal-dual learning procedure. The former indicates the optimality loss induced by the dual transformation and the latter characterizes the limiting error of the iterative algorithm, both of which guarantee the performance of the variance-constrained learning. Through numerical simulations, we corroborate our theoretical findings and observe a strong expected performance with a controllable standard deviation.


A Primal-Dual Algorithmic Framework for Constrained Convex Minimization

We present a primal-dual algorithmic framework to obtain approximate sol...

Stochastic Graph Neural Networks

Graph neural networks (GNNs) model nonlinear representations in graph da...

Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process

The problem of constrained Markov decision process (CMDP) is investigate...

Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave Maximization

Iterative Hard Thresholding (IHT) is a class of projected gradient desce...

Stochastic Variance Reduced Primal Dual Algorithms for Empirical Composition Optimization

We consider a generic empirical composition optimization problem, where ...

Model-Free Learning of Optimal Ergodic Policies in Wireless Systems

Learning optimal resource allocation policies in wireless systems can be...

Please sign up or login with your details

Forgot password? Click here to reset