Semi-supervised Sequence Classification through Change Point Detection

Sequential sensor data is generated in a wide variety of realworld applications. A fundamental machine learning challenge involves learning effective classifiers for such sequential data. While deep learning has led to impressive performance gains in recent years within domains such as speech, this has relied on the availability of large datasets of sequences with high-quality labels. In many applications, however, the associated class labels are often extremely limited, with precise labelling/segmentation being too expensive to perform in a high volume. However, large amounts of unlabeled data may still be available. In this paper we propose a novel framework for semi-supervised learning in such contexts. In an unsupervised manner, change point detection methods can be used to identify instances where classes change within a sequence. We show that change points provide examples of similar/dissimilar pairs of sequences which, when coupled with class labels, can be used in a semisupervised classification setting. Pairs from labels and change points are used by a neural network to learn improved representations for classification. We provide extensive synthetic simulations and show that the learned representations are better than those learned through an autoencoder and obtain improved results on simulations and human activity recognition datasets.

Authors

• Nauman Ahad
• Mark A. Davenport

Keywords

No keywords are indexed for this paper.