TensorLearn
Back to Course
Deep Learning with PyTorch
Module 11 of 12

11. Graph Neural Networks

1. Non-Euclidean Data

Images are grids. Text is a line. Molecules and Social Networks are Graphs. Convolution doesn't work here. We need Message Passing.

2. Message Passing

A node updates its state by aggregating information from its neighbors. Library: torch_geometric.

Mark as Completed

TensorLearn - AI Engineering for Professionals