From the course: Learning Graph Neural Networks
Join today to access over 24,900 courses taught by industry experts.
Exercise: Setting up a graph convolutional network
From the course: Learning Graph Neural Networks
Exercise: Setting up a graph convolutional network
- [Instructor] Previously, we trained a baseline model using dense neural networks for node classification. This model only took into account the node features, did not take into account the structure of the graph. So the connections in the graph, the citations from one paper to another, those were not considered in the node classification problem. If you think about it, our graph represents a citation network. Documents that belong to a certain class or category are more likely to cite documents that belong to the same class or category, and this is something that we've not taken advantage of so far. In this movie, we'll use a graph convolutional network to take into account the structure of the graph as well as the node features for node classification. We'll use the graph convolutional layer available in PyTorch Geometric, which will take into account the neighboring node information to generate embeddings for each node that will then be used for classification. The graph…
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.