The statistical information of the four individual time series datasets is shown in Table 1.

Neural Information Processing Systems http://nips.cc/

Each dataset contains miscellaneous series, categorized into six domains (micro, industry, macro, finance, demographic, other). Thus, atime series regression dataset consists ofT input-target pairs: {(X1,y1),...,(XT,yT). For each synthesized training set withT samples, we synthesize100T samples as the testing set. D.3 Models The NN we use has six fully-connected layers with ReLU activation function and three residual connections. D.4 Results There are three methods tobe compared.

Foundation models pre-trained on large-scale source datasets are reshaping the traditional training paradigm for time series classification. However, existing time series foundation models primarily focus on forecasting tasks and often overlook classification-specific challenges, such as modeling interpretable shapelets that capture class-discriminative temporal features. To bridge this gap, we propose UniShape, a unified shape-aware foundation model designed for time series classification. UniShape incorporates a shape-aware adapter that adaptively aggregates multiscale discriminative subsequences (shapes) into class tokens, effectively selecting the most relevant subsequence scales to enhance model interpretability. Meanwhile, a prototype-based pretraining module is introduced to jointly learn instance- and shape-level representations, enabling the capture of transferable shape patterns. Pre-trained on a large-scale multi-domain time series dataset comprising 1.89 million samples, UniShape exhibits superior generalization across diverse target domains. Experiments on 128 UCR datasets and 30 additional time series datasets demonstrate that UniShape achieves state-of-the-art classification performance, with interpretability and ablation analyses further validating its effectiveness.

Deep Neural Networks (DNNs) have been criticized because they easily overfit noisy (incorrect) labels. To improve the robustness of DNNs, existing methods for image data regard samples with small training losses as correctly labeled data (small-loss criterion). Nevertheless, time series' discriminative patterns are easily distorted by external noises (i.e., frequency perturbations) during the recording process. This results in training losses of some time series samples that do not meet the small-loss criterion. Therefore, this paper proposes a deep learning paradigm called Scale-teaching to cope with time series noisy labels. Specifically, we design a fine-to-coarse cross-scale fusion mechanism for learning discriminative patterns by utilizing time series at different scales to train multiple DNNs simultaneously. Meanwhile, each network is trained in a cross-teaching manner by using complementary information from different scales to select small-loss samples as clean labels. For unselected large-loss samples, we introduce multi-scale embedding graph learning via label propagation to correct their labels by using selected clean samples. Experiments on multiple benchmark time series datasets demonstrate the superiority of the proposed Scale-teaching paradigm over state-of-the-art methods in terms of effectiveness and robustness.

The receptive field (RF), which determines the region of time series to be "seen" and used, is critical to improve the performance for time series classification (TSC). However, the variation of signal scales across and within time series data, makes it challenging to decide on proper RF sizes for TSC. In this paper, we propose a dynamic sparse network (DSN) with sparse connections for TSC, which can learn to cover various RF without cumbersome hyper-parameters tuning. The kernels in each sparse layer are sparse and can be explored under the constraint regions by dynamic sparse training, which makes it possible to reduce the resource cost. The experimental results show that the proposed DSN model can achieve state-of-art performance on both univariate and multivariate TSC datasets with less than 50% computational cost compared with recent baseline methods, opening the path towards more accurate resource-aware methods for time series analyses.

Kernel-based methods such as Rocket are among the most effective default approaches for univariate time series classification (TSC), yet they do not perform equally well across all datasets. We revisit the long-standing intuition that different representations capture complementary structure and show that selectively fusing them can yield consistent improvements over Rocket on specific, systematically identifiable kinds of datasets. We introduce Fusion-3 (F3), a lightweight framework that adaptively fuses Rocket, Sax, and Sfa representations. To understand when fusion helps, we cluster UCR datasets into six groups using meta-features capturing series length, spectral structure, roughness, and class imbalance, and treat these clusters as interpretable data-structure regimes. Our analysis shows that fusion typically outperforms strong baselines in regimes with structured variability or rich frequency content, while offering diminishing returns in highly irregular or outlier-heavy settings. To support these findings, we combine three complementary analyses: non-parametric paired statistics across datasets, ablation studies isolating the roles of individual representations, and attribution via SHAP to identify which dataset properties predict fusion gains. Sample-level case studies further reveal the underlying mechanism: fusion primarily improves performance by rescuing specific errors, with adaptive increases in frequency-domain weighting precisely where corrections occur. Using 5-fold cross-validation on the 113 UCR datasets, F3 yields small but consistent average improvements over Rocket, supported by frequentist and Bayesian evidence and accompanied by clearly identifiable failure cases. Our results show that selectively applied fusion provides dependable and interpretable extension to strong kernel-based methods, correcting their weaknesses precisely where the data support it.

Understanding and distinguishing temporal patterns in time series data is essential for scientific discovery and decision-making. For example, in biomedical research, uncovering meaningful patterns in physiological signals can improve diagnosis, risk assessment, and patient outcomes. However, existing methods for time series pattern discovery face major challenges, including high computational complexity, limited interpretability, and difficulty in capturing meaningful temporal structures. To address these gaps, we introduce a novel learning framework that jointly trains two Transformer models using complementary time series representations: shapelet-based representations to capture localized temporal structures and traditional feature engineering to encode statistical properties. The learned shapelets serve as interpretable signatures that differentiate time series across classification labels. Additionally, we develop a visual analytics system -- SigTIme -- with coordinated views to facilitate exploration of time series signatures from multiple perspectives, aiding in useful insights generation. We quantitatively evaluate our learning framework on eight publicly available datasets and one proprietary clinical dataset. Additionally, we demonstrate the effectiveness of our system through two usage scenarios along with the domain experts: one involving public ECG data and the other focused on preterm labor analysis.

Classical Time Series Classification algorithms are dominated by feature engineering strategies. One of the most prominent of these transforms is ROCKET, which achieves strong performance through random kernel features. We introduce SPROCKET (Selected Prototype Random Convolutional Kernel Transform), which implements a new feature engineering strategy based on prototypes. On a majority of the UCR and UEA Time Series Classification archives, SPROCKET achieves performance comparable to existing convolutional algorithms and the new MR-HY-SP ( MultiROCKET-HYDRA-SPROCKET) ensemble's average accuracy ranking exceeds HYDRA-MR, the previous best convolutional ensemble's performance. These experimental results demonstrate that prototype-based feature transformation can enhance both accuracy and robustness in time series classification.