Graph Convolutional Networks, Graph Conventional Networks are a generalised version of Convolutional Neural Networks. They are an extension of the generic convolutional operation and have the ability to deal with non-Euclidean types of data and can easily work with nodes and graphs to get features to learn and train the networks. They have evolved over time and have been applied to various domains. The techniques have improved and the performance of the Graph Convolutional Networks has been a great tool in the domain of research. In this study, we present the transformations and improvements of Graph Convolutional Networks and analyse the variation of the contrast between the traditional convolutional neural network and the graph neural network. The different applications have been discussed, adaptations have been highlighted along with the limitations.

Keywords : Graph Convolutional Network.