$k$-Graph: A Graph Embedding for Interpretable Time Series Clustering

2025-02-18

AI Summary

Existing time-series clustering methods suffer from poor interpretability, typically yielding opaque, black-box cluster centroids. To address this, we propose *k-graph*, an interpretable unsupervised clustering framework based on multi-scale graph embedding: it automatically extracts multi-scale subsequences via sliding windows and constructs an interpretable subsequence relational graph; leverages graph neural networks for unsupervised graph embedding—supporting variable-length time series without requiring predefined subsequence lengths; and enables cluster explanations grounded in salient, domain-meaningful subsequence patterns. Evaluated on multiple benchmark datasets, *k-graph* achieves an average 3.2% higher clustering accuracy than state-of-the-art methods. It is the first approach to unify high clustering performance with structured, pattern-level, and multi-scale interpretability in time-series clustering.

Technology Category

• Machine Learning: Clustering
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text

Abstract

Time series clustering poses a significant challenge with diverse applications across domains. A prominent drawback of existing solutions lies in their limited interpretability, often confined to presenting users with centroids. In addressing this gap, our work presents $k$-Graph, an unsupervised method explicitly crafted to augment interpretability in time series clustering. Leveraging a graph representation of time series subsequences, $k$-Graph constructs multiple graph representations based on different subsequence lengths. This feature accommodates variable-length time series without requiring users to predetermine subsequence lengths. Our experimental results reveal that $k$-Graph outperforms current state-of-the-art time series clustering algorithms in accuracy, while providing users with meaningful explanations and interpretations of the clustering outcomes.

Problem

• Enhances interpretability in time series clustering
• Utilizes graph representation for variable-length series
• Outperforms existing algorithms in accuracy and clarity

Innovation

• Graph embedding for time series
• Unsupervised interpretability enhancement
• Variable-length subsequence graph representations