Название: Responsible Graph Neural Networks
Автор: Mohamed Abdel-Basset, Nour Moustafa, Hossam Hawash
Издательство: CRC Press
Год: 2023
Страниц: 324
Язык: английский
Формат: pdf (true)
Размер: 10.29 MB

More frequent and complex cyber threats require robust, automated, and rapid responses from cyber-security specialists. This book offers a complete study in the area of graph learning in cyber, emphasizing graph neural networks (GNNs) and their cyber-security applications.

Three parts examine the basics, methods and practices, and advanced topics. The first part presents a grounding in graph data structures and graph embedding and gives a taxonomic view of GNNs and cyber-security applications. The second part explains three different categories of graph learning, including deterministic, generative, and reinforcement learning and how they can be used for developing cyber defense models. The discussion of each category covers the applicability of simple and complex graphs, scalability, representative algorithms, and technical details.

The main objective of this book is to provide scholars and readers with in-depth understanding of the “graph intelligence” as a special branch of Artificial Intelligence (AI). The book provides great emphasis on the role of Deep Learning in revolutionizing the graph intelligence tasks in a broad range of applications reliant graph-structured data. Given the exploding amount of daily generated data containing complex interaction among different entities, the graph-based solutions gain an increased interest when it comes to developing intelligent applications. With the elasticity and generalization ability of Deep Learning, this book provides a detailed explanation of different families of graph-based Deep Learning solutions that have been achieving the state-of-the-art graph representational learning performance. This book is introduced to fill the apparent gaps in practical and conceptual information about the potential of Deep Learning for modeling complex representations from different types of graphs.

To get you up and running for the hands-on learning experience, we need to set you up with an environment for running Python, Jupyter notebooks, the relevant libraries, and the code needed to run the book itself. The simplest way to get going will be to install Anaconda Framework. The Python 3.x version is required. Before installing the Pytorch framework, please first check whether or not you have proper GPUs on your machine (the GPUs that power the display on a standard laptop do not count for our purposes). If you are installing on a GPU server, you need to install CUDA-enabled Pytorch. Otherwise, you can install the CPU version as follows. That will be more than enough horsepower to get you through the first few chapters, but you will want to access GPUs before running larger models. Online GPU platforms (Google Colab) can also be used to run the examples in this book. Following this, the readers are required to install Pytorch_Geometric and DGL libraries to be able to run the graph intelligence methods discussed across different chapters of this book.

Undergraduate students, graduate students, researchers, cyber analysts, and AI engineers looking to understand practical deep learning methods will find this book an invaluable resource.