DE-GCN: Differential Evolution as an optimization algorithm for Graph Convolutional Networks

Neural networks had impressive results in recent years. Although neural networks only performed using Euclidean data in past decades, many data-sets in the real world have graph structures. This gap led researchers to implement deep learning on graphs. The graph convolutional network (GCN) is one of the graph neural networks. We propose the differential evolutional optimization method as an optimizer for GCN instead of gradient-based methods in this work. Hence the differential evolution algorithm applies for graph convolutional network’s training and parameter optimization. The node classification task is a non-convex problem. Therefore DE algorithm is suitable for these kinds of complex problems. Implementing evolutionally algorithms on GCN and parameter optimization are explained and compared with traditional GCN. DE-GCN outperforms and improves the results by powerful local and global searches. It also decreases the training time.