Graph Neural Network Operators: a Review

Graph Neural Networks (GNN) is one of the promising machine learning areas in solving real world problems such as social networks, recommender systems, computer vision and pattern recognition. One of the important component of GNN is GNN operators which are responsible to train GNN graph structured data and forward learning nodes information to other layers. This review focus on recent advancements of GNN operators in detail. The rich Mathematical nature of GNN operators has been discussed for selected GNN operators. The review also highlights different benchmark graph structured datasets and presents results using different GNN operators. We have included thorough discussion for state-of-the-art in this field including limitations and future directions. Overall, the review covers important areas of GNN as GNN operators from future research directions point of view and real world applications perspective.