Metric Learning (Synthesis Lectures on Artificial Intelligence and Machine Learning)

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.

物體之間的相似性在人類的認知過程和人工系統的識別和分類中扮演著重要角色。如何適當地測量給定任務的相似性對於許多機器學習、模式識別和數據挖掘方法的性能至關重要。本書專注於度量學習，這是一組從數據中自動學習相似性和距離函數的技術，在過去十年中在機器學習和相關領域引起了很大的興趣。在本書中，我們對度量學習文獻進行了全面的回顧，包括算法、理論和數值和結構數據的應用。我們首先介紹相關定義和經典的度量函數，以及它們在機器學習和數據挖掘中的應用示例。然後，我們回顧了各種度量學習算法，從線性距離和相似性學習的簡單設置開始。我們展示了如何將這些方法擴展到非常大量的訓練數據。為了超越線性情況，我們討論了學習非線性度量或在特徵空間中學習多個線性度量的方法，並回顧了多任務和半監督學習等更複雜情況的方法。儘管大部分現有的工作都集中在數值數據上，我們還涵蓋了度量學習在結構化數據（如字符串、樹、圖和時間序列）上的文獻。在本書的技術部分，我們介紹了一些最近用於分析度量學習的泛化性能的統計框架，並對先前介紹的一些算法結果進行了推導。最後，我們通過一系列成功應用於計算機視覺、生物信息學和信息檢索的實際問題來說明度量學習的相關性。