Graph-Based Sparse Neural Networks for Traffic Signal Optimization

We investigate the performance of sparsely connected neural networks, with connectivity determined by road network graphs, for solving the Traffic Signal Setting optimization problem. We conducted experiments on three realistic road network topologies and found these types of graph neural networks superior to fully connected ones, both in terms of generalization properties on fixed test sets and—more importantly—near target function minima obtained in the gradient descent optimization process. We additionally confirm the soundness of our method by showing that random perturbations of the actual graph lead to consistent deterioration of model performance.