# Time2Graph: Revisiting Time Series Modeling with Dynamic Shapelets

arXiv: https://arxiv.org/abs/1911.04143 · HTML: https://mlsanity.com/paper/1911.04143/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2019.

## Built on by (most cited first, 12 of 12)

- [A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection](https://mlsanity.com/paper/2307.03759/) (2023)
- [Event2Graph: Event-driven Bipartite Graph for Multivariate Time-series Anomaly Detection](https://mlsanity.com/paper/2108.06783/) (2021)
- [MTS2Graph: Interpretable Multivariate Time Series Classification with Temporal Evolving Graphs](https://mlsanity.com/paper/2306.03834/) (2023)
- [Expressing Multivariate Time Series as Graphs with Time Series Attention Transformer](https://mlsanity.com/paper/2208.09300/) (2022)
- [TSGDiff: Rethinking Synthetic Time Series Generation from a Pure Graph Perspective](https://mlsanity.com/paper/2511.12174/) (2025)
- [Graph Neural Alchemist: An innovative fully modular architecture for time series-to-graph classification](https://mlsanity.com/paper/2410.09307/) (2024)
- [CAND: Cross-Domain Ambiguity Inference for Early Detecting Nuanced Illness Deterioration](https://mlsanity.com/paper/2501.16365/) (2025)
- [Early Detection of Patient Deterioration from Real-Time Wearable Monitoring System](https://mlsanity.com/paper/2505.01305/) (2025)
- [Fast Mining and Dynamic Time-to-Event Prediction over Multi-sensor Data Streams](https://mlsanity.com/paper/2601.04741/) (2026)
- [Causal Discovery from Time-Series Data with Short-Term Invariance-Based Convolutional Neural Networks](https://mlsanity.com/paper/2408.08023/) (2024)
- [To See or To Read: User Behavior Reasoning in Multimodal LLMs](https://mlsanity.com/paper/2511.03845/) (2025)
- [Versatile and Risk-Sensitive Cardiac Diagnosis via Graph-Based ECG Signal Representation](https://mlsanity.com/paper/2511.07973/) (2025)

## Abstract (arXiv)

Time series modeling has attracted extensive research efforts; however, achieving both reliable efficiency and interpretability from a unified model still remains a challenging problem. Among the literature, shapelets offer interpretable and explanatory insights in the classification tasks, while most existing works ignore the differing representative power at different time slices, as well as (more importantly) the evolution pattern of shapelets. In this paper, we propose to extract time-aware shapelets by designing a two-level timing factor. Moreover, we define and construct the shapelet evolution graph, which captures how shapelets evolve over time and can be incorporated into the time series embeddings by graph embedding algorithms. To validate whether the representations obtained in this way can be applied effectively in various scenarios, we conduct experiments based on three public time series datasets, and two real-world datasets from different domains. Experimental results clearly show the improvements achieved by our approach compared with 17 state-of-the-art baselines.