Graph Neural Networks: A Deep Neural Network for Graphs
Explore different Graph Neural Networks (GNN): GCN, GraphSAGE, and GAT
Prerequisites: Graph Basics and Application of Graph
Good to read: Graph Representational Learning
Graph Neural Network(GNN) is a powerful generic framework for defining deep learning models aiming at addressing graph-related tasks in an end-to-end manner
GNNs goal is to generate representations for nodes or any feature information based on the structure of the Graph.
GNNs uses a form of neural message passing where vector messages are exchanged between nodes and updated using neural network.
GNNs combine node feature information with the Graph structure by recursively passing neural messages along edges of the input Graph.
GNNs are divided into two main streams, spectral-based approaches and spatial-based approaches.
Spatial-based graph approach is simple and works on the graph topology by aggregating local node neighborhood information. The spatial graph-based techniques are preferred over spectral graphs as they are efficient due to less computational…
