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.

The book deals with questions which arise from storing a graph in a computer. Different classes of graphs admit different forms of computer representations, and focusing on the representations gives a new perspective on a number of problems. For a variety of classes of graphs, the book considers such questions as existence of good representations, algorithms for finding representations, questions of characterizations in terms of representation, and how the representation affects the complexity of optimization problems. General models of efficient computer representations are also considered. The book is designed to be used both as a text for a graduate course on topics related to graph representation, and as a monograph for anyone interested in research in the field of graph representation. The material is of interest both to those focusing purely on graph theory and to those working in the area of graph algorithms.

A comprehensive review of an area of machine learning that deals with the use of unlabeled data in classification problems: state-of-the-art algorithms, a taxonomy of the field, applications, benchmark experiments, and directions for future research. In the field of machine learning, semi-supervised learning (SSL) occupies the middle ground, between supervised learning (in which all training examples are labeled) and unsupervised learning (in which no label data are given). Interest in SSL has increased in recent years, particularly because of application domains in which unlabeled data are plentiful, such as images, text, and bioinformatics. This first comprehensive overview of SSL presents state-of-the-art algorithms, a taxonomy of the field, selected applications, benchmark experiments, and perspectives on ongoing and future research.Semi-Supervised Learning first presents the key assumptions and ideas underlying the field: smoothness, cluster or low-density separation, manifold structure, and transduction. The core of the book is the presentation of SSL methods, organized according to algorithmic strategies. After an examination of generative models, the book describes algorithms that implement the low-density separation assumption, graph-based methods, and algorithms that perform two-step learning. The book then discusses SSL applications and offers guidelines for SSL practitioners by analyzing the results of extensive benchmark experiments. Finally, the book looks at interesting directions for SSL research. The book closes with a discussion of the relationship between semi-supervised learning and transduction.

The current exponential growth in graph data has forced a shift to parallel computing for executing graph algorithms. Implementing parallel graph algorithms and achieving good parallel performance have proven difficult. This book addresses these challenges by exploiting the well-known duality between a canonical representation of graphs as abstract collections of vertices and edges and a sparse adjacency matrix representation. This linear algebraic approach is widely accessible to scientists and engineers who may not be formally trained in computer science. The authors show how to leverage existing parallel matrix computation techniques and the large amount of software infrastructure that exists for these computations to implement efficient and scalable parallel graph algorithms. The benefits of this approach are reduced algorithmic complexity, ease of implementation, and improved performance.

The Boost Graph Library (BGL) is the first C++ library to apply the principles of generic programming to the construction of the advanced data structures and algorithms used in graph computations. Problems in such diverse areas as Internet packet routing, molecular biology, scientific computing, and telephone network design can be solved by using graph theory. This book presents an in-depth description of the BGL and provides working examples designed to illustrate the application of BGL to these real-world problems. Written by the BGL developers, The Boost Graph Library: User Guide and Reference Manual gives you all the information you need to take advantage of this powerful new library. Part I is a complete user guide that begins by introducing graph concepts, terminology, and generic graph algorithms. This guide also takes the reader on a tour through the major features of the BGL; all motivated with example problems. Part II is a comprehensive reference manual that provides complete documentation of all BGL concepts, algorithms, and classes. Readers will find coverage of: Graph terminology and concepts Generic programming techniques in C++ Shortest-path algorithms for Internet routing Network planning problems using the minimum-spanning tree algorithms BGL algorithms with implicitly defined graphs BGL Interfaces to other graph libraries BGL concepts and algorithms BGL classes–graph, auxiliary, and adaptor Groundbreaking in its scope, this book offers the key to unlocking the power of the BGL for the C++ programmer looking to extend the reach of generic programming beyond the Standard Template Library.

This book constitutes the refereed proceedings of the 5th IAPR International Workshop on Graph-Based Representations in Pattern Recognition, GbRPR 2005, held in Poitiers, France in April 2005. The 18 revised full papers and 17 revised poster papers presented were carefully reviewed and selected from 50 submissions. The papers are organized in topical sections on graph representations, graphs and linear representations, combinatorial maps, matching, hierarchical graph abstraction and matching, inexact