LTSpAUC: Learning Time-Series Shapelets for Partial AUC Maximization

Abstract

Shapelets are discriminative segments used to classify time-series instances. Shapelet methods that jointly learn both classifiers and shapelets have been studied in recent years because such methods provide both interpretable results and superior accuracy. The partial area under the receiver operating characteristic curve (pAUC) for a low range of false-positive rates (FPR) is an important performance measure for practical cases in industries such as medicine, manufacturing, and maintenance. In this article, we propose a method that jointly learns both shapelets and a classifier for pAUC optimization in any FPR range, including the full AUC. In addition, we propose the following two extensions for shapelet methods: (1) reducing algorithmic complexity in time-series length to linear time and (2) explicitly determining the classes that shapelets tend to match. Comparing with state-of-theart learning-based shapelet methods, we demonstrated the superiority of pAUC on UCR time-series data sets and its effectiveness in industrial case studies from medicine, manufacturing, and maintenance.

AUC Maximization in the Era of Big Data and AI: A Survey

“…Fourth, different theoretical guarantees have been examined, e.g., consistency [45], generalization error bounds [84], excess risk bounds [54,170], regret bounds [178], convergence rates or sample complexities [89], stability [85,163]. Last but not least, AUC maximization has been successfully investigated in a variety of applications [7,10,40,57,69,132,135,146,147,156,181,184], e.g., medical image classification [173] and molecular properties prediction [151], to mention but a few.…”