Home  | Publications | STS25

Towards Explainable Deep Clustering for Time Series Data

MCML Authors

Link to Profile Thomas Seidl PI Matchmaking

Thomas Seidl

Prof. Dr.

Director

Database Systems, Data Mining and AI

Abstract

Deepclustering uncovers hidden patterns and groups incomplex time series data, yet its opaque decision-making limits use in safety-critical settings. This survey offers a structured overview of explainable deep clustering for time series, collecting current methods and their realworld applications. We thoroughly discuss and compare peer-reviewed and preprint papers through application domains across healthcare, finance, IoT, and climate science. Our analysis reveals that most work relies on autoencoder and attention architectures, with limited support for streaming, irregularly sampled, or privacy-preserved series, and interpretability is still primarily treated as an add-on. To push the field forward, we outline six research opportunities: (1) combining complex networks with built-in interpretability; (2) setting up clear, faithfulness-focused evaluation metrics for unsupervised explanations; (3) building explainers that adapt to live data streams; (4) crafting explanations tailored to specific domains; (5) adding human-in-the-loop methods that refine clusters and explanations together; and (6) improving our understanding of how time series clustering models work internally. By making interpretability a primary design goal rather than an afterthought, we propose the groundwork for the next generation of trustworthy deep clustering time series analytics.

inproceedings

TempXAI @ECML-PKDD 2025

Workshop Explainable AI for Time Series and Data Streams at European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. Porto, Portugal, Sep 15-19, 2025. To be published.

Authors

U. Schlegel • G. M. Tavares • T. Seidl

Research Area

 A3 | Computational Models

BibTeXKey: STS25

Back to Top