Interpretable Spectral Variational AutoEncoder (ISVAE) for time series clustering

TL;DR

This paper introduces ISVAE, an interpretable spectral variational autoencoder with a filter bank bottleneck that enhances clustering interpretability and performance in time series data.

Contribution

The paper proposes a novel VAE architecture with an interpretable filter bank bottleneck, improving interpretability, clusterability, and hierarchical insights in time series clustering.

Findings

Outperforms state-of-the-art clustering methods on real datasets

Produces interpretable and separable encodings

Generates a hierarchical tree of cluster similarities

Abstract

The best encoding is the one that is interpretable in nature. In this work, we introduce a novel model that incorporates an interpretable bottleneck-termed the Filter Bank (FB)-at the outset of a Variational Autoencoder (VAE). This arrangement compels the VAE to attend on the most informative segments of the input signal, fostering the learning of a novel encoding ${f_0}$ which boasts enhanced interpretability and clusterability over traditional latent spaces. By deliberately constraining the VAE with this FB, we intentionally constrict its capacity to access broad input domain information, promoting the development of an encoding that is discernible, separable, and of reduced dimensionality. The evolutionary learning trajectory of ${f_0}$ further manifests as a dynamic hierarchical tree, offering profound insights into cluster similarities. Additionally, for handling intricate data configurations, we propose a tailored decoder structure that is symmetrically aligned with FB's architecture. Empirical evaluations highlight the superior efficacy of ISVAE, which compares favorably to state-of-the-art results in clustering metrics across real-world datasets.