Graph machine learning is rapidly reshaping how we model complex relationships--and this book offers one of the most comprehensive, practice oriented guides to mastering it from the ground up. Designed for readers who want both conceptual clarity and hands on capability, it distills the essential foundations of graph representation, graph embedding, and graph neural networks into a clear, structured learning path.
Across fifteen chapters, the book moves from fundamental graph concepts to advanced Graph Neural Network (GNN) architectures, trustworthy graph learning, spectral methods, heterogeneous graphs, and emerging graph foundation models. It not only explains the design logic behind modern graph learning algorithms but also reveals why certain models succeed--or fail--across real world tasks. Readers will explore practical scenarios in social recommendation, financial risk control, and scientific intelligence, gaining the ability to translate theory into effective solutions. The book also highlights frontier directions such as dynamic graphs, hypergraphs, large scale graph learning, and multimodal integration.
This book is ideal for university students, engineers, and technical professionals seeking a rigorous yet accessible entry point into graph machine learning. With its combination of conceptual frameworks, platform tools, code implementations, and application case studies, it equips readers to build, optimize, and deploy graph models with confidence--requiring only basic machine learning literacy as a starting point.
外文書商品之書封,為出版社提供之樣本。實際出貨商品,以出版社所提供之現有版本為主。部份書籍,因出版社供應狀況特殊,匯率將依實際狀況做調整。
無庫存之商品,在您完成訂單程序之後,將以空運的方式為你下單調貨。為了縮短等待的時間,建議您將外文書與其他商品分開下單,以獲得最快的取貨速度,平均調貨時間為1~2個月。
為了保護您的權益,「三民網路書店」提供會員七日商品鑑賞期(收到商品為起始日)。
若要辦理退貨,請在商品鑑賞期內寄回,且商品必須是全新狀態與完整包裝(商品、附件、發票、隨貨贈品等)否則恕不接受退貨。