Introduction to Graph Neural Networks using TF-GNN
A Graph Neural Network (GNN) is an optimizable transformation on all attributes of the graph that preserves graph symmetries (permutation invariances). GNNs explore the relationships among data samples to learn high-quality node, edge, and graph representations. GNNs have applications in diverse domains like information retrieval, recommendations, fraud detection, knowledge representation, bioinformatics, drug discoveries, material science, physics, and circuit design. This talk will cover the introduction to Graph Neural Networks and implementation of GNNs using TensorFlow GNN.
Usha Rengaraju, Chief Research Officer at Exa Protocol