Structure and Relationships: Graph Neural Networks and a Pytorch Implementation

Understanding the mathematical background of graph neural networks and implementation for a regression problem in pytorch

Introduction

Interconnected graphical data is all around us, ranging from molecular structures to social networks and design structures of cities. Graph Neural Networks (GNNs) are emerging as a powerful method of modelling and learning the spatial and graphical structure of such data. It has been applied to protein structures and other molecular applications such as drug discovery as well as modelling systems such as …

cities data deep learning design gnns graph graph neural networks implementation machine learning modelling networks neural networks pytorch regression relationships social social networks spatial understanding