Deep Multiple Metric Learning for Time Series Classification

Effective distance metric plays an important role in time series classification. Metric learning, which aims to learn a data-adaptive distance metric to measure the distance among samples, has achieved promising results on time series classification. However, most existing approaches focus on learning a single linear metric, which is unsuitable for nonlinear relationships and heterogeneous datasets with locality information. Besides, the hard samples in the training set account for only a small part, which may fail to characterize the global geometry of the metric embedding space. In this paper, we propose a novel deep multiple metric learning (DMML) method for time series classification. DMML contains a convolutional network component to extract nonlinear features of time series. For exploiting locality information, the last feature layer of the convolutional network is divided into several nonoverlapping groups and a separate metric learner is built on each group to get multiple metrics. In order to reduce the correlations among learners and facilitate robust metric learning, we design an adversarial negative generator to synthesize different hard negative complements for different metric learners. Moreover, an auxiliary loss is introduced to increase the robustness of DMML for the magnitude of distance. Extensive experiments on UCR datasets demonstrate the effectiveness of DMML for time series classification.

Automated summary

The study proposes a novel deep multiple metric learning (DMML) method for time series classification. It utilizes a convolutional network to extract nonlinear features of time series and builds multiple metric learners to obtain multiple metrics for exploiting locality information. An adversarial negative generator and an auxiliary loss are introduced to increase the robustness of the method for the magnitude of distance.