Graph-structured data is ubiquitous throughout the natural and social sciences, from telecommunication networks to quantum chemistry. Building relational inductive biases into deep learning architectures is crucial for creating systems that can learn, reason, and generalize from this kind of data. Recent years have seen a surge in research on graph representation learning, including techniques for deep graph embeddings, generalizations of convolutional neural networks to graph-structured data, and neural message-passing approaches inspired by belief propagation. These advances in graph representation learning have led to new state-of-the-art results in numerous domains, including chemical synthesis, 3D vision, recommender systems, question answering, and social network analysis. This book provides a synthesis and overview of graph representation learning. It begins with a discussion of the goals of graph representation learning as well as key methodological foundations in graph theory and network analysis. Following this, the book introduces and reviews methods for learning node embeddings, including random-walk-based methods and applications to knowledge graphs. It then provides a technical synthesis and introduction to the highly successful graph neural network (GNN) formalism, which has become a dominant and fast-growing paradigm for deep learning with graph data. The book concludes with a synthesis of recent advancements in deep generative models for graphs—a nascent but quickly growing subset of graph representation learning.

This book introduces readers to a workload-aware methodology for large-scale graph algorithm optimization in graph-computing systems, and proposes several optimization techniques that can enable these systems to handle advanced graph algorithms efficiently. More concretely, it proposes a workload-aware cost model to guide the development of high-performance algorithms. On the basis of the cost model, the book subsequently presents a system-level optimization resulting in a partition-aware graph-computing engine, PAGE. In addition, it presents three efficient and scalable advanced graph algorithms – the subgraph enumeration, cohesive subgraph detection, and graph extraction algorithms. This book offers a valuable reference guide for junior researchers, covering the latest advances in large-scale graph analysis; and for senior researchers, sharing state-of-the-art solutions based on advanced graph algorithms. In addition, all readers will find a workload-aware methodology for designing efficient large-scale graph algorithms.

Wring more out of the data with a scientific approach to analysis Graph Analysis and Visualization brings graph theory out of the lab and into the real world. Using sophisticated methods and tools that span analysis functions, this guide shows you how to exploit graph and network analytic techniques to enable the discovery of new business insights and opportunities. Published in full color, the book describes the process of creating powerful visualizations using a rich and engaging set of examples from sports, finance, marketing, security, social media, and more. You will find practical guidance toward pattern identification and using various data sources, including Big Data, plus clear instruction on the use of software and programming. The companion website offers data sets, full code examples in Python, and links to all the tools covered in the book. Science has already reaped the benefit of network and graph theory, which has powered breakthroughs in physics, economics, genetics, and more. This book brings those proven techniques into the world of business, finance, strategy, and design, helping extract more information from data and better communicate the results to decision-makers. Study graphical examples of networks using clear and insightful visualizations Analyze specifically-curated, easy-to-use data sets from various industries Learn the software tools and programming languages that extract insights from data Code examples using the popular Python programming language There is a tremendous body of scientific work on network and graph theory, but very little of it directly applies to analyst functions outside of the core sciences – until now. Written for those seeking empirically based, systematic analysis methods and powerful tools that apply outside the lab, Graph Analysis and Visualization is a thorough, authoritative resource.

Graph Embedding for Pattern Recognition covers theory methods, computation, and applications widely used in statistics, machine learning, image processing, and computer vision. This book presents the latest advances in graph embedding theories, such as nonlinear manifold graph, linearization method, graph based subspace analysis, L1 graph, hypergraph, undirected graph, and graph in vector spaces. Real-world applications of these theories are spanned broadly in dimensionality reduction, subspace learning, manifold learning, clustering, classification, and feature selection. A selective group of experts contribute to different chapters of this book which provides a comprehensive perspective of this field.

Wring more out of the data with a scientific approach to analysis Graph Analysis and Visualization brings graph theory out of the lab and into the real world. Using sophisticated methods and tools that span analysis functions, this guide shows you how to exploit graph and network analytic techniques to enable the discovery of new business insights and opportunities. Published in full color, the book describes the process of creating powerful visualizations using a rich and engaging set of examples from sports, finance, marketing, security, social media, and more. You will find practical guidance toward pattern identification and using various data sources, including Big Data, plus clear instruction on the use of software and programming. The companion website offers data sets, full code examples in Python, and links to all the tools covered in the book. Science has already reaped the benefit of network and graph theory, which has powered breakthroughs in physics, economics, genetics, and more. This book brings those proven techniques into the world of business, finance, strategy, and design, helping extract more information from data and better communicate the results to decision-makers. Study graphical examples of networks using clear and insightful visualizations Analyze specifically-curated, easy-to-use data sets from various industries Learn the software tools and programming languages that extract insights from data Code examples using the popular Python programming language There is a tremendous body of scientific work on network and graph theory, but very little of it directly applies to analyst functions outside of the core sciences – until now. Written for those seeking empirically based, systematic analysis methods and powerful tools that apply outside the lab, Graph Analysis and Visualization is a thorough, authoritative resource.

Soft computing, as an engineering science, and statistics, as a classical branch of mathematics, emphasize different aspects of data analysis. Soft computing focuses on obtaining working solutions quickly, accepting approximations and unconventional approaches. Its strength lies in its flexibility to create models that suit the needs arising in applications. In addition, it emphasizes the need for intuitive and interpretable models, which are tolerant to imprecision and uncertainty. Statistics is more rigorous and focuses on establishing objective conclusions based on experimental data by analyzing the possible situations and their (relative) likelihood. It emphasizes the need for mathematical methods and tools to assess solutions and guarantee performance. Combining the two fields enhances the robustness and generalizability of data analysis methods, while preserving the flexibility to solve real-world problems efficiently and intuitively.