Название: Graph Learning Techniques
Автор: Baoling Shan, Xin Yuan, Wei Ni, Ren Ping Liu, Eryk Dutkiewicz
Издательство: CRC Press
Год: 2025
Страниц: 186
Язык: английский
Формат: pdf (true), epub
Размер: 23.4 MB

This comprehensive guide addresses key challenges at the intersection of Data Science, Graph Learning, and privacy preservation. It begins with foundational graph theory, covering essential definitions, concepts, and various types of graphs. The book bridges the gap between theory and application, equipping readers with the skills to translate theoretical knowledge into actionable solutions for complex problems. It includes practical insights into brain network analysis and the dynamics of COVID-19 spread. The guide provides a solid understanding of graphs by exploring different graph representations and the latest advancements in graph learning techniques. It focuses on diverse graph signals and offers a detailed review of state-of-the-art methodologies for analyzing these signals. A major emphasis is placed on privacy preservation, with comprehensive discussions on safeguarding sensitive information within graph structures. The book also looks forward, offering insights into emerging trends, potential challenges, and the evolving landscape of privacy-preserving graph learning.

Graphs serve as a widely recognized representation of the network structure of interconnected data. They appear in various application domains, including social systems, ecosystems, biological networks, knowledge graphs, and information systems. As Artificial Intelligence technologies continue to advance, Graph Learning (i.e., Machine Learning applied to graphs) is attracting increasing interest from both researchers and practitioners. This approach has proven effective for numerous tasks, such as classification, link prediction, and matching, by utilizing Machine Learning algorithms to extract pertinent features from graphs. A critical challenge is to excavate graphs underlying observed signals because of non-convex problem structure and associated high computational requirements.

This resource is a valuable reference for advance undergraduate and postgraduate students in courses related to Network Analysis, Privacy and Security in Data Analytics, and Graph Theory and Applications in Healthcare.