![Applied Graph Data Science: Graph Algorithms and Platforms, Knowledge Graphs, Neural Networks, and Applied Use Cases Applied Graph Data Science: Graph Algorithms and Platforms, Knowledge Graphs, Neural Networks, and Applied Use Cases](/images/libros/NoImagen.jpg)
Applied Graph Data Science: Graph Algorithms and Platforms, Knowledge Graphs, Neural Networks, and Applied Use Cases
Raj, Pethuru
Dutta, Pushan Kumar
Chong, Peter Han Joo
Song, Houbing Herbert
Zaitsev, Dmitry A.
Applied Graph Data Science: Graph Algorithms and Platforms, Knowledge Graphs, Neural Networks, and Applied Use Cases delineates how graph data science significantly empowers the application of data science. The book discusses the emerging paradigm of graph data science in detail along with its practical research and real-world applications. Readers will be enriched with the knowledge of graph data science, graph analytics, algorithms, databases, platforms, and use cases across a variety of research and topics and applications. This book also presents how graphs are used as a programming language, especially demonstrating how Sleptsov Net Computing can contribute as an entirely graphical concurrent processing language for supercomputers. Graph data science is emerging as an expressive and illustrative data structure for optimally representing a variety of data types and their insightful relationships. These data structures include graph query languages, databases, algorithms, and platforms. From here, powerful analytics methods and machine learning/deep learning (ML/DL) algorithms are quickly evolving to analyze and make sense out of graph data. As a result, ground-breaking use cases across scientific research topics and industry verticals are being developed using graph data representation and manipulation. A wide range of complex business and scientific research requirements are efficiently represented and solved through graph data analysis, and Applied Graph Data Science gives readers both the conceptual foundations and technical methods for applying these powerful techniques. Provides comprehensive coverage of the emerging paradigm of graph data science and its real-world applicationsGives readers practical guidance on how to approach and solve complex data analysis problems using graph data science, with an emphasis on deep analysis techniques including, graph neural networks (GNNs), machine learning, algorithms, graph databases, and graph query languagesCovers extended graph models: bipartite directed graphs of place-transition nets, graphs with dynamical processes defined on them - Petri and Sleptsov nets, and graphs as programming languagesPresents all the key tools and techniques as well as the foundations of graph theory, including mathematical concepts, research, and graph analytics INDICE: 1. Demystifying Digital Transformation Technologies and Tools2. Demystifying the Graph Data Science (GDS) Paradigm3. The Graph Technology4. Illustrating the Key Drivers of Graph Analytics5. Depicting the Graph Algorithms6. Illustrating Graph Analytics7. Feature Engineering Methods for Graph Data Science8. Graph Databases and Toolkits9. Graph Query Languages10. Hardware Accelerators for Graph Data Science11. The Graph Data Science Platforms and Frameworks12. The Emergence of Graph Neural Networks (GNNs)13. Graph Neural Networks (GNNs): the Use Cases
- ISBN: 978-0-443-29654-3
- Editorial: Morgan Kaufmann
- Encuadernacion: Rústica
- Páginas: 250
- Fecha Publicación: 01/02/2025
- Nº Volúmenes: 1
- Idioma: Inglés