Book Image

Mastering PyTorch - Second Edition

By : Ashish Ranjan Jha
4 (1)
Book Image

Mastering PyTorch - Second Edition

4 (1)
By: Ashish Ranjan Jha

Overview of this book

PyTorch is making it easier than ever before for anyone to build deep learning applications. This PyTorch deep learning book will help you uncover expert techniques to get the most out of your data and build complex neural network models. You’ll build convolutional neural networks for image classification and recurrent neural networks and transformers for sentiment analysis. As you advance, you'll apply deep learning across different domains, such as music, text, and image generation, using generative models, including diffusion models. You'll not only build and train your own deep reinforcement learning models in PyTorch but also learn to optimize model training using multiple CPUs, GPUs, and mixed-precision training. You’ll deploy PyTorch models to production, including mobile devices. Finally, you’ll discover the PyTorch ecosystem and its rich set of libraries. These libraries will add another set of tools to your deep learning toolbelt, teaching you how to use fastai to prototype models and PyTorch Lightning to train models. You’ll discover libraries for AutoML and explainable AI (XAI), create recommendation systems, and build language and vision transformers with Hugging Face. By the end of this book, you'll be able to perform complex deep learning tasks using PyTorch to build smart artificial intelligence models.
Table of Contents (21 chapters)
20
Index

Types of graph learning tasks

We have discussed graphs and the basic principles of GNNs but what type of tasks can be performed using GNNs on graph data? (By tasks, we are referring to the downstream tasks mentioned in the previous section.) Broadly, there are three different categories of graph learning tasks:

  • Node-level tasks
  • Edge-level tasks
  • Graph-level tasks

Let us briefly discuss these.

Understanding node-level tasks

Node-level tasks are aimed at predicting the class of a given node within a graph. Our demonstrations in the previous sections (in Figure 6.3) are based on node-level tasks where the task was to predict the gender of each node – male, female, or other. For such tasks, the latent feature representations of each node (final output of the node’s computational graph) are used to train a downstream task.

This task can be:

  • A classification task – involving discrete labels (gender, color, etc.)
  • ...