In many realistic scenarios, large volumes of time series data are generated with limited or expensive annotations. This limitation makes supervised learning methods difficult to apply and leads to the use of unsupervised approaches capable of discovering meaningful structures directly from raw data.
arXiv:2607. 07258v1 Announce Type: cross Abstract: In many realistic scenarios, large volumes of time series data are generated with limited or expensive annotations.
arXiv:2609.36873v1 Announce Type: new Abstract: Multivariate Time Series (MTS) clustering is an important tool in temporal data mining, aiming to discover latent group structures from complex observa...
arXiv:2606. 12077v1 Announce Type: new Abstract: Time-series clustering remains challenging due to the inherent trade-off between clustering effectiveness and computational efficiency.
arXiv:2511. 20577v5 Announce Type: replace Abstract: Real-world time series often exhibit strong non-stationarity, complex nonlinear dynamics, and behavior expressed across multiple temporal scales, from rapid local fluctuations to slow-evolving long-range trends.
arXiv:2604. 16325v3 Announce Type: replace-cross Abstract: Multivariate time series forecasting is fundamental to numerous domains such as energy, finance, and environmental monitoring, where complex temporal dependencies and cross-variable interactions pose enduring challenges.
The paper introduces the Progressive Memory Transformer (PMT), a transformer variant that adds writable, window‑aligned memory to expose mid‑range representations alongside token and sequence‑level outputs. PMT is trained with a hierarchical learning framework that applies separate objectives at local, mid‑range, and global scales, encouraging the model to capture fine‑grained variation, window‑level motifs, and overall sequence agreement. Experiments on seven UCR/UEA/UCI classification datasets, a cue‑retention probe, and forecasting tasks show that PMT achieves strong low‑label classification performance, competitive multi‑horizon forecasting, and evidence that its memory states encode mid‑range motifs.
The paper examines whether Deep Embedded Clustering (DEC) truly overcomes the fundamental limitations of k‑means clustering, such as handling clusters of arbitrary shapes, varied sizes, and densities. Through analysis, it finds that DEC does not exploit the underlying data distribution and therefore fails to address these limitations. Instead, a non‑deep learning approach that leverages distributional information of clusters can achieve the intended goals of deep clustering.
WinoTS introduces a wavelet‑based self‑distillation framework for time‑series models that uses time‑frequency augmentations to create multi‑scale structural views, avoiding distortion of signal dynamics. The method outperforms state‑of‑the‑art baselines in long‑term forecasting, cross‑domain zero‑shot transfer, and unsupervised anomaly detection, and linear probing on frozen representations often beats fully supervised training from scratch. Ablation studies show WinoTS is architecture‑agnostic and demonstrates that time‑frequency transformations offer a principled alternative to vision‑style spatial augmentations.
arXiv:2502. 15637v2 Announce Type: replace-cross Abstract: While foundation models have revolutionized various domains, their application to time series classification remains rather under-explored, with existing literature predominantly focused on forecasting.
arXiv:2602. 08638v2 Announce Type: replace-cross Abstract: As a fundamental data mining task, unsupervised time series anomaly detection (TSAD) aims to build a model for identifying abnormal timestamps without assuming the availability of annotations.
Phase-Consistent Magnetic Spectral Learning for Multi-View Clustering proposes a new unsupervised method that uses a complex-valued magnetic affinity to capture both magnitude and phase information across multiple data views. By deriving a confidence-directed cross-view flow from anchor assignments and combining it with a nonnegative magnitude backbone, the approach constructs a Hermitian magnetic Laplacian that yields a stable shared spectral signal for representation learning and clustering. Experiments on ten public benchmarks show the method outperforms or matches leading MVC baselines on most dataset-metric combinations.
arXiv:2509. 25289v4 Announce Type: replace-cross Abstract: Identifying an effective clustering algorithm for a given dataset remains a fundamental unsupervised learning issue.