Graph Neural Networks

In this part we are going to learn more about graphs concepts then we explain simple example about how to read karate club datasets: after this part we are ready to dig into graph convolution neural networks. Data(x None, edge_index None) is a plain old python object modeling a single graph with various (optional) attributes. The recent success of graph neural networks(GNNs) for analyzing the graphs' domain has attracted more researchers in this field. CNN is a type of deep learning model for processing data that has a sequence or grid pattern(text, images), which is inspired by the visual system of mammals organization and designed to automatically and adaptively multi-scale localized features, from low-to-high-level patterns. CNN is a mathematical framework typically composed of three types of layers ( convolution, pooling, and fully connected layers), and they apply for object detection, speech recognition, and other Euclidean data structures.