Skip to main content

Graph Convolutional Networks

Difficulty level

This lecture covers the concepts of the architecture and convolution of traditional convolutional neural networks, the characteristics of graph and graph convolution, and spectral graph convolutional neural networks and how to perform spectral convolution, as well as the complete spectrum of Graph Convolutional Networks (GCNs), starting with the implementation of Spectral Convolution through Spectral Networks. It then provides insights on applicability of the other convolutional definition of Template Matching to graphs, leading to Spatial networks. This lecture is a part of the Deep Learning Course at CDS, a course that covered the latest techniques in deep learning and representation learning, focusing on supervised and unsupervised deep learning, embedding methods, metric learning, convolutional and recurrent nets, with applications to computer vision, natural language understanding, and speech recognition. Prerequisites for this module include: Modules 1 - 5 of this course and Introduction to Data Science or a Graduate Level Machine Learning.

Topics covered in this lesson


0:00:50 – Architecture of Traditional ConvNets
0:13:11 – Convolution of Traditional ConvNets
0:25:29 – Spectral Convolution
0:44:30 – Spectral GCNs
1:06:04 – Template Matching, Isotropic GCNs and Benchmarking GNNs
1:33:06 – Anisotropic GCNs and Conclusion