From the course: Learning Graph Neural Networks
Join today to access over 24,800 courses taught by industry experts.
Summary and next steps
From the course: Learning Graph Neural Networks
Summary and next steps
- [Instructor] And this demo brings us to the very end of this course on learning graph neural networks. Here's a quick overview of what we covered in this course. The first part was focused on understanding different kinds of graphs. We looked at directed and undirected graphs, weighted and unweighted graphs. We discussed homogeneous and heterogeneous graphs, bipartite and folded graphs, amongst others. Moving on from basic graph concepts, we discussed graph machine learning approaches. This included classic graph algorithms, representation learning using non neural network techniques, and the third approach, graph neural networks. We then discussed the intuition behind graph neural networks. We understood how the idea of convolution works with arbitrary graph topologies. We discussed message passing using graph transformations and aggregations and with all of these concepts under our belt, we moved on to hands-on demos. We first understood the graph data structure used by PyTorch…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.