DPSOM: Deep Probabilistic Clustering with Self-Organizing Maps
This work addresses the need for interpretable visualizations in applications like medical analysis by improving clustering performance while maintaining visualization properties, though it is incremental as it builds on existing methods like VAEs and SOMs.
The paper tackled the problem of combining clustering and representation learning for interpretable visualizations by introducing DPSOM, a deep probabilistic clustering method using self-organizing maps, which achieved superior clustering performance on datasets like MNIST/Fashion-MNIST and outperformed baselines in time-series clustering and forecasting on medical data.
Generating interpretable visualizations from complex data is a common problem in many applications. Two key ingredients for tackling this issue are clustering and representation learning. However, current methods do not yet successfully combine the strengths of these two approaches. Existing representation learning models which rely on latent topological structure such as self-organising maps, exhibit markedly lower clustering performance compared to recent deep clustering methods. To close this performance gap, we (a) present a novel way to fit self-organizing maps with probabilistic cluster assignments (PSOM), (b) propose a new deep architecture for probabilistic clustering (DPSOM) using a VAE, and (c) extend our architecture for time-series clustering (T-DPSOM), which also allows forecasting in the latent space using LSTMs. We show that DPSOM achieves superior clustering performance compared to current deep clustering methods on MNIST/Fashion-MNIST, while maintaining the favourable visualization properties of SOMs. On medical time series, we show that T-DPSOM outperforms baseline methods in time series clustering and time series forecasting, while providing interpretable visualizations of patient state trajectories and uncertainty estimation.