Graph Convolutional Networks Lecture
Network theory has very many application areas, where graphs are of primary importance, in e.g.,:
-Communication networks
-Epidemiology
-Systems Biology
-Social networks.
Social Media (e.g., Twitter, Facebook, Instagram, to name a few) has had a tremendous growth in the past 20 years. Social Media Analysis has very many applications, e.g.,:
-Recommendation Systems
-Sentiment Analysis
-Information Diffusion
-Web Search.
This lecture overviews Graph Convolutional Networks (GCN) that have many applications in Deep Learning, Signal and Video Analysis, Network Theory, Web Science and Social Media Analytics. It covers the following topics in detail: Graph Convolutions. Empirical Risk Minimization with Graph Signals. Learning with Graph Convolutional Filters. Learning with Graph Perceptrons. GCN Types. GCN general architecture. Spectral Graph Convolution, Simple Spectral GCN, Spline GCN, LapGCN, ChebNet, CayleyNet. Spatial Graph Convolution, Simple Spatial GCN, GraphSage, GIN, MoNet, GAT, GatedGCN. GCN from scratch with numpy. Spatio-Temporal GCN.