From the course: Learning Graph Neural Networks
Unlock this course with a free trial
Join today to access over 24,400 courses taught by industry experts.
The graph neural network architecture
From the course: Learning Graph Neural Networks
The graph neural network architecture
- [Presenter] Now that we understand the basic structure of graph neural networks, let's consider an example graph and look at the computation graph for a particular node, and let's discuss the general neural network architecture and the operations that it performs on the graph data. Here is our example graph structure. We have a number of nodes and we have a number of interconnections between nodes. Now, we are going to discuss the computation graph for a particular target node, and here, the target node I've considered is node A. The structure of the neural network for each target node is going to be different, so we are going to consider just one node at a time. For each target node, the first layer of the neural network will only consider nodes that are immediate adjacent neighbors of the target node. The neural network layers of a graph are used to generate node embeddings based on the local structure of the neighborhood around the target node. The first layer of the neural…
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.