Variational pSOM: Deep Probabilistic Clustering with Self-Organizing Maps

Laura Manduchi, Matthias Hüser, Gunnar Rätsch, Vincent Fortuin

TL;DR: We present a new deep architecture, VarPSOM, and its extension to time series data, VarTPSOM, which achieve superior clustering performance compared to current deep clustering methods on static and temporal data.

Abstract:

Generating visualizations and interpretations from high-dimensional data is a
common problem in many fields. Two key approaches for tackling this problem
are clustering and representation learning. There are very performant deep
clustering models on the one hand and interpretable representation learning techniques,
often relying on latent topological structures such as self-organizing maps,
on the other hand. However, current methods do not yet successfully combine
these two approaches. We present a new deep architecture for probabilistic clustering,
VarPSOM, and its extension to time series data, VarTPSOM, composed of VarPSOM
modules connected by LSTM cells. We show that they achieve superior
clustering performance compared to current deep clustering methods on static
MNIST/Fashion-MNIST data as well as medical time series, while inducing an
interpretable representation. Moreover, on the medical time series, VarTPSOM
successfully predicts future trajectories in the original data space.

Keywords: Self-organizing maps, Generative models, Unsupervised representation learning

Community Implementations: [ 3 code implementations](https://www.catalyzex.com/paper/arxiv:1910.01590/code)