From the course: Learning Graph Neural Networks
Join today to access over 24,400 courses taught by industry experts.
Graph neural networks intuition
From the course: Learning Graph Neural Networks
Graph neural networks intuition
- [Instructor] Before we get to the mechanics and mathematics of how graph neural networks work, let's understand the intuition behind graph neural networks, and that's what we'll focus on in this movie. Now, the objective of graph neural networks is to generate embeddings for nodes and edges using the features of nodes and edges as well as local neighborhood information, the structure of the graph. In order to do this, the core idea behind GNNs borrow from convolutional neural networks. Convolutional neural networks have a convolutional layer where a sliding window kernel is slid over the input images, and this kernel is used to extract and aggregate the features of nearby pixels in an image. In the convolutional layer of a convolutional neural network, you define a kernel whose weights are found during the training process of the model. This kernel is slid over the input image and helps extract features from the underlying image. The kernel aggregates the neighborhood information…
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.
