Dissimilarity-Preserving Representation Learning for One-Class Time Series Classification

• Published in: IEEE transaction on neural networks and learning systems Vol. 35; no. 10; pp. 13951 - 13962
• Main Authors: Mauceri, Stefano, Sweeney, James, Nicolau, Miguel, McDermott, James
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.10.2024
• Subjects: Approximation algorithms; Autoencoders; Autoencoders (AEs); Convolutional neural networks; Neural networks; one-class classification; Representation learning; Time measurement; Time series analysis; time series classification
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2023.3273503

We propose to embed time series in a latent space where pairwise Euclidean distances (EDs) between samples are equal to pairwise dissimilarities in the original space, for a given dissimilarity measure. To this end, we use auto-encoder (AE) and encoder-only neural networks to learn elastic dissimilarity measures, e.g., dynamic time warping (DTW), that are central to time series classification (Bagnall et al., 2017). The learned representations are used in the context of one-class classification (Mauceri et al., 2020) on the datasets of UCR/UEA archive (Dau et al., 2019). Using a 1-nearest neighbor (1NN) classifier, we show that learned representations allow classification performance that is close to that of raw data, but in a space of substantially lower dimensionality. This implies substantial and compelling savings in terms of computational and storage requirements for nearest neighbor time series classification.