Similarity between objects plays an important role in both human cognitive processes and artificial systems for recognition and categorization. How to appropriately measure such similarities for a given task is crucial to the performance of many machine learning, pattern recognition and data mining methods. This book is devoted to metric learning, a set of techniques to automatically learn similarity and distance functions from data that has attracted a lot of interest in machine learning and related fields in the past ten years. In this book, we provide a thorough review of the metric learning literature that covers algorithms, theory and applications for both numerical and structured data. We first introduce relevant definitions and classic metric functions, as well as examples of their use in machine learning and data mining. We then review a wide range of metric learning algorithms, starting with the simple setting of linear distance and similarity learning. We show how one may scale-up these methods to very large amounts of training data. To go beyond the linear case, we discuss methods that learn nonlinear metrics or multiple linear metrics throughout the feature space, and review methods for more complex settings such as multi-task and semi-supervised learning. Although most of the existing work has focused on numerical data, we cover the literature on metric learning for structured data like strings, trees, graphs and time series. In the more technical part of the book, we present some recent statistical frameworks for analyzing the generalization performance in metric learning and derive results for some of the algorithms presented earlier. Finally, we illustrate the relevance of metric learning in real-world problems through a series of successful applications to computer vision, bioinformatics and information retrieval. Table of Contents: Introduction / Metrics / Properties of Metric Learning Algorithms / Linear Metric Learning / Nonlinear and Local Metric Learning / Metric Learning for Special Settings / Metric Learning for Structured Data / Generalization Guarantees for Metric Learning / Applications / Conclusion / Bibliography / Authors' Biographies

Autorentext

Aurélien Bellet received his Ph.D. in Machine Learning from the University of Saint-Etienne (France) in 2012. His work focused on algorithmic and theoretical aspects of metric and similarity learning. After completing his thesis, he was a postdoctoral researcher at the University of Southern California, where he worked on large-scale and distributed machine learning with applications to automatic speech recognition. He is currently a postdoctoral researcher at Telecom ParisTech (France), working on machine learning for big data.Amaury Habrard received a Ph.D. in Machine Learning in 2004 from the University of Saint-Etienne. He was Assistant Professor at the Laboratoire dInformatique Fondamentale of Aix-Marseille University until 2011, where he received a habilitation thesis in 2010. He is currently Professor in the Machine Learning group at the Hubert Curien laboratory of the University of Saint-Etienne. His research interests include metric learning, transfer learning, online learningand learning theory.Marc Sebban received a Ph.D. in Machine Learning in 1996 from the Universite of Lyon 1. After four years spent at the French West Indies and Guyana University as Assistant Professor, he got a position of Professor in 2002 at the University of Saint-Etienne (France). Since 2010, he is the head of the Machine Learning group and the director of the Computer Science, Cryptography and Imaging department of the Hubert Curien laboratory. His research interests focus on ensemble methods, metric learning, transfer learning and more generally on statistical learning theory.