This paper introduces a novel Graph Neural Network (GNN) architecture for time series classification, based on visibility graph representations. Traditional time series classification methods often struggle with high computational complexity and inadequate capture of spatio-temporal dynamics. By representing time series as visibility graphs, it is possible to encode both spatial and temporal dependencies inherent to time series data, while being computationally efficient. Our architecture is fully modular, enabling flexible experimentation with different models and representations. We employ directed visibility graphs encoded with in-degree and PageRank features to improve the representation of time series, ensuring efficient computation while enhancing the model's ability to capture long-range dependencies in the data. We show the robustness and generalization capability of the proposed architecture across a diverse set of classification tasks and against a traditional model. Our work represents a significant advancement in the application of GNNs for time series analysis, offering a powerful and flexible framework for future research and practical implementations.
In recent years, Edge AI has become more prevalent with applications across various industries, from environmental monitoring to smart city management. Edge AI facilitates the processing of Internet of Things (IoT) data and provides privacy-enabled and latency-sensitive services to application users using Machine Learning (ML) algorithms, e.g., Time Series Classification (TSC). However, existing TSC algorithms require access to full raw data and demand substantial computing resources to train and use them effectively in runtime. This makes them impractical for deployment in resource-constrained Edge environments. To address this, in this paper, we propose an Adaptive Brownian Bridge-based Symbolic Aggregation Vector Space Model (ABBA-VSM). It is a new TSC model designed for classification services on Edge. Here, we first adaptively compress the raw time series into symbolic representations, thus capturing the changing trends of data. Subsequently, we train the classification model directly on these symbols. ABBA-VSM reduces communication data between IoT and Edge devices, as well as computation cycles, in the development of resource-efficient TSC services on Edge. We evaluate our solution with extensive experiments using datasets from the UCR time series classification archive. The results demonstrate that the ABBA-VSM achieves up to 80% compression ratio and 90-100% accuracy for binary classification. Whereas, for non-binary classification, it achieves an average compression ratio of 60% and accuracy ranging from 60-80%.
The Greenland Ice Sheet (GrIS) has emerged as a significant contributor to global sea level rise, primarily due to increased meltwater runoff. Supraglacial lakes, which form on the ice sheet surface during the summer months, can impact ice sheet dynamics and mass loss; thus, better understanding these lakes' seasonal evolution and dynamics is an important task. This study presents a computationally efficient time series classification approach that uses Gaussian Mixture Models (GMMs) of the Reconstructed Phase Spaces (RPSs) to identify supraglacial lakes based on their seasonal evolution: 1) those that refreeze at the end of the melt season, 2) those that drain during the melt season, and 3) those that become buried, remaining liquid insulated a few meters beneath the surface. Our approach uses time series data from the Sentinel-1 and Sentinel-2 satellites, which utilize microwave and visible radiation, respectively. Evaluated on a GrIS-wide dataset, the RPS-GMM model, trained on a single representative sample per class, achieves 85.46% accuracy with Sentinel-1 data alone and 89.70% with combined Sentinel-1 and Sentinel-2 data. This performance significantly surpasses existing machine learning and deep learning models which require a large training data. The results demonstrate the robustness of the RPS-GMM model in capturing the complex temporal dynamics of supraglacial lakes with minimal training data.
Large language models (LLMs) have shown remarkable in-context learning (ICL) capabilities on textual data. We explore whether these capabilities can be extended to continuous vectors from diverse domains, obtained from black-box pretrained encoders. By aligning input data with an LLM's embedding space through lightweight projectors, we observe that LLMs can effectively process and learn from these projected vectors, which we term Vector-ICL. In particular, we find that pretraining projectors with general language modeling objectives enables Vector-ICL, while task-specific finetuning further enhances performance. In our experiments across various tasks and modalities, including text reconstruction, numerical function regression, text classification, summarization, molecule captioning, time-series classification, graph classification, and fMRI decoding, Vector-ICL often surpasses both few-shot ICL and domain-specific model or tuning. We further conduct analyses and case studies, indicating the potential of LLMs to process vector representations beyond traditional token-based paradigms.
While the majority of time series classification research has focused on modeling fixed-length sequences, variable-length time series classification (VTSC) remains critical in healthcare, where sequence length may vary among patients and events. To address this challenge, we propose $\textbf{S}$tochastic $\textbf{S}$parse $\textbf{S}$ampling (SSS), a novel VTSC framework developed for medical time series. SSS manages variable-length sequences by sparsely sampling fixed windows to compute local predictions, which are then aggregated and calibrated to form a global prediction. We apply SSS to the task of seizure onset zone (SOZ) localization, a critical VTSC problem requiring identification of seizure-inducing brain regions from variable-length electrophysiological time series. We evaluate our method on the Epilepsy iEEG Multicenter Dataset, a heterogeneous collection of intracranial electroencephalography (iEEG) recordings obtained from four independent medical centers. SSS demonstrates superior performance compared to state-of-the-art (SOTA) baselines across most medical centers, and superior performance on all out-of-distribution (OOD) unseen medical centers. Additionally, SSS naturally provides post-hoc insights into local signal characteristics related to the SOZ, by visualizing temporally averaged local predictions throughout the signal.
Medical time series (MedTS) classification suffers from poor generalizability in real-world deployment due to inter- and intra-dataset heterogeneity, such as varying numbers of channels, signal lengths, task definitions, and patient characteristics. To address this, we propose FORMED, a novel framework for repurposing a backbone foundation model, pre-trained on generic time series, to enable highly generalizable MedTS classification on unseen datasets. FORMED combines the backbone with a novel classifier comprising two components: (1) task-specific channel embeddings and label queries, dynamically sized to match any number of channels and target classes, and (2) a shared decoding attention layer, jointly trained across datasets to capture medical domain knowledge through task-agnostic feature-query interactions. After repurposing, FORMED achieves seamless adaptation to unseen MedTS datasets through lightweight label query training (0.1% of parameters), eliminating the need for full fine-tuning or architectural redesign. We evaluate FORMED on 5 diverse MedTS datasets, benchmarking against 11 Task-Specific Models (TSM) and 4 Task-Specific Adaptation (TSA) methods. Our results demonstrate FORMED's dominant performance, achieving up to 35% absolute improvement in F1-score (on ADFTD dataset) over specialized baselines. Further analysis reveals consistent generalization across varying channel configurations, time series lengths, and clinical tasks, which are key challenges in real-world deployment. By decoupling domain-invariant representation learning from task-specific adaptation, FORMED establishes a scalable and resource-efficient paradigm for foundation model repurposing in healthcare. This approach prioritizes clinical adaptability over rigid task-centric design, offering a practical pathway for real-world implementation.
RF-GAP has recently been introduced as an improved random forest proximity measure. In this paper, we present PF-GAP, an extension of RF-GAP proximities to proximity forests, an accurate and efficient time series classification model. We use the forest proximities in connection with Multi-Dimensional Scaling to obtain vector embeddings of univariate time series, comparing the embeddings to those obtained using various time series distance measures. We also use the forest proximities alongside Local Outlier Factors to investigate the connection between misclassified points and outliers, comparing with nearest neighbor classifiers which use time series distance measures. We show that the forest proximities seem to exhibit a stronger connection between misclassified points and outliers than nearest neighbor classifiers.
Major solar flares are abrupt surges in the Sun's magnetic flux, presenting significant risks to technological infrastructure. In view of this, effectively predicting major flares from solar active region magnetic field data through machine learning methods becomes highly important in space weather research. Magnetic field data can be represented in multivariate time series modality where the data displays an extreme class imbalance due to the rarity of major flare events. In time series classification-based flare prediction, the use of contrastive representation learning methods has been relatively limited. In this paper, we introduce CONTREX, a novel contrastive representation learning approach for multivariate time series data, addressing challenges of temporal dependencies and extreme class imbalance. Our method involves extracting dynamic features from the multivariate time series instances, deriving two extremes from positive and negative class feature vectors that provide maximum separation capability, and training a sequence representation embedding module with the original multivariate time series data guided by our novel contrastive reconstruction loss to generate embeddings aligned with the extreme points. These embeddings capture essential time series characteristics and enhance discriminative power. Our approach shows promising solar flare prediction results on the Space Weather Analytics for Solar Flares (SWAN-SF) multivariate time series benchmark dataset against baseline methods.
Transfer learning is a common practice that alleviates the need for extensive data to train neural networks. It is performed by pre-training a model using a source dataset and fine-tuning it for a target task. However, not every source dataset is appropriate for each target dataset, especially for time series. In this paper, we propose a novel method of selecting and using multiple datasets for transfer learning for time series classification. Specifically, our method combines multiple datasets as one source dataset for pre-training neural networks. Furthermore, for selecting multiple sources, our method measures the transferability of datasets based on shapelet discovery for effective source selection. While traditional transferability measures require considerable time for pre-training all the possible sources for source selection of each possible architecture, our method can be repeatedly used for every possible architecture with a single simple computation. Using the proposed method, we demonstrate that it is possible to increase the performance of temporal convolutional neural networks (CNN) on time series datasets.
Tensor decomposition has emerged as a prominent technique to learn low-dimensional representation under the supervision of reconstruction error, primarily benefiting data inference tasks like completion and imputation, but not classification task. We argue that the non-uniqueness and rotation invariance of tensor decomposition allow us to identify the directions with largest class-variability and simple graph Laplacian can effectively achieve this objective. Therefore we propose a novel Pseudo Laplacian Contrast (PLC) tensor decomposition framework, which integrates the data augmentation and cross-view Laplacian to enable the extraction of class-aware representations while effectively capturing the intrinsic low-rank structure within reconstruction constraint. An unsupervised alternative optimization algorithm is further developed to iteratively estimate the pseudo graph and minimize the loss using Alternating Least Square (ALS). Extensive experimental results on various datasets demonstrate the effectiveness of our approach.
Foundation models, while highly effective, are often resource-intensive, requiring substantial inference time and memory. This paper addresses the challenge of making these models more accessible with limited computational resources by exploring dimensionality reduction techniques. Our goal is to enable users to run large pre-trained foundation models on standard GPUs without sacrificing performance. We investigate classical methods such as Principal Component Analysis alongside neural network-based adapters, aiming to reduce the dimensionality of multivariate time series data while preserving key features. Our experiments show up to a 10x speedup compared to the baseline model, without performance degradation, and enable up to 4.5x more datasets to fit on a single GPU, paving the way for more user-friendly and scalable foundation models.
Tiny Machine Learning (TinyML) enables efficient, lowcost, and privacy preserving machine learning inference directly on microcontroller units (MCUs) connected to sensors. Optimizing models for these constrained environments is crucial. This paper investigates how reducing data acquisition rates affects TinyML models for time series classification, focusing on resource-constrained, battery operated IoT devices. By lowering data sampling frequency, we aim to reduce computational demands RAM usage, energy consumption, latency, and MAC operations by approximately fourfold while maintaining similar classification accuracies. Our experiments with six benchmark datasets (UCIHAR, WISDM, PAMAP2, MHEALTH, MITBIH, and PTB) showed that reducing data acquisition rates significantly cut energy consumption and computational load, with minimal accuracy loss. For example, a 75\% reduction in acquisition rate for MITBIH and PTB datasets led to a 60\% decrease in RAM usage, 75\% reduction in MAC operations, 74\% decrease in latency, and 70\% reduction in energy consumption, without accuracy loss. These results offer valuable insights for deploying efficient TinyML models in constrained environments.
Multivariate time series classification is an important task with widespread domains of applications. Recently, deep neural networks (DNN) have achieved state-of-the-art performance in time series classification. However, they often require large expert-labeled training datasets which can be infeasible in practice. In few-shot settings, i.e. only a limited number of samples per class are available in training data, DNNs show a significant drop in testing accuracy and poor generalization ability. In this paper, we propose to address these problems from an optimization and a loss function perspective. Specifically, we propose a new learning framework named COSCO consisting of a sharpness-aware minimization (SAM) optimization and a Prototypical loss function to improve the generalization ability of DNN for multivariate time series classification problems under few-shot setting. Our experiments demonstrate our proposed method outperforms the existing baseline methods. Our source code is available at: https://github.com/JRB9/COSCO.
In time-series classification, understanding model decisions is crucial for their application in high-stakes domains such as healthcare and finance. Counterfactual explanations, which provide insights by presenting alternative inputs that change model predictions, offer a promising solution. However, existing methods for generating counterfactual explanations for time-series data often struggle with balancing key objectives like proximity, sparsity, and validity. In this paper, we introduce TX-Gen, a novel algorithm for generating counterfactual explanations based on the Non-dominated Sorting Genetic Algorithm II (NSGA-II). TX-Gen leverages evolutionary multi-objective optimization to find a diverse set of counterfactuals that are both sparse and valid, while maintaining minimal dissimilarity to the original time series. By incorporating a flexible reference-guided mechanism, our method improves the plausibility and interpretability of the counterfactuals without relying on predefined assumptions. Extensive experiments on benchmark datasets demonstrate that TX-Gen outperforms existing methods in generating high-quality counterfactuals, making time-series models more transparent and interpretable.
The selection of algorithms is a crucial step in designing AI services for real-world time series classification use cases. Traditional methods such as neural architecture search, automated machine learning, combined algorithm selection, and hyperparameter optimizations are effective but require considerable computational resources and necessitate access to all data points to run their optimizations. In this work, we introduce a novel data fingerprint that describes any time series classification dataset in a privacy-preserving manner and provides insight into the algorithm selection problem without requiring training on the (unseen) dataset. By decomposing the multi-target regression problem, only our data fingerprints are used to estimate algorithm performance and uncertainty in a scalable and adaptable manner. Our approach is evaluated on the 112 University of California riverside benchmark datasets, demonstrating its effectiveness in predicting the performance of 35 state-of-the-art algorithms and providing valuable insights for effective algorithm selection in time series classification service systems, improving a naive baseline by 7.32% on average in estimating the mean performance and 15.81% in estimating the uncertainty.
Functional data analysis (FDA) and ensemble learning can be powerful tools for analyzing complex environmental time series. Recent literature has highlighted the key role of diversity in enhancing accuracy and reducing variance in ensemble methods.This paper introduces Randomized Spline Trees (RST), a novel algorithm that bridges these two approaches by incorporating randomized functional representations into the Random Forest framework. RST generates diverse functional representations of input data using randomized B-spline parameters, creating an ensemble of decision trees trained on these varied representations. We provide a theoretical analysis of how this functional diversity contributes to reducing generalization error and present empirical evaluations on six environmental time series classification tasks from the UCR Time Series Archive. Results show that RST variants outperform standard Random Forests and Gradient Boosting on most datasets, improving classification accuracy by up to 14\%. The success of RST demonstrates the potential of adaptive functional representations in capturing complex temporal patterns in environmental data. This work contributes to the growing field of machine learning techniques focused on functional data and opens new avenues for research in environmental time series analysis.
This article presents a new approach based on MiniRocket, called SelF-Rocket, for fast time series classification (TSC). Unlike existing approaches based on random convolution kernels, it dynamically selects the best couple of input representations and pooling operator during the training process. SelF-Rocket achieves state-of-the-art accuracy on the University of California Riverside (UCR) TSC benchmark datasets.
Deep learning models have been shown to be a powerful solution for Time Series Classification (TSC). State-of-the-art architectures, while producing promising results on the UCR and the UEA archives , present a high number of trainable parameters. This can lead to long training with high CO2 emission, power consumption and possible increase in the number of FLoating-point Operation Per Second (FLOPS). In this paper, we present a new architecture for TSC, the Light Inception with boosTing tEchnique (LITE) with only 2.34% of the number of parameters of the state-of-the-art InceptionTime model, while preserving performance. This architecture, with only 9, 814 trainable parameters due to the usage of DepthWise Separable Convolutions (DWSC), is boosted by three techniques: multiplexing, custom filters, and dilated convolution. The LITE architecture, trained on the UCR, is 2.78 times faster than InceptionTime and consumes 2.79 times less CO2 and power. To evaluate the performance of the proposed architecture on multivariate time series data, we adapt LITE to handle multivariate time series, we call this version LITEMV. To bring theory into application, we also conducted experiments using LITEMV on multivariate time series representing human rehabilitation movements, showing that LITEMV not only is the most efficient model but also the best performing for this application on the Kimore dataset, a skeleton based human rehabilitation exercises dataset. Moreover, to address the interpretability of LITEMV, we present a study using Class Activation Maps to understand the classification decision taken by the model during evaluation.
Recently, the issue of adversarial robustness in the time series domain has garnered significant attention. However, the available defense mechanisms remain limited, with adversarial training being the predominant approach, though it does not provide theoretical guarantees. Randomized Smoothing has emerged as a standout method due to its ability to certify a provable lower bound on robustness radius under $\ell_p$-ball attacks. Recognizing its success, research in the time series domain has started focusing on these aspects. However, existing research predominantly focuses on time series forecasting, or under the non-$\ell_p$ robustness in statistic feature augmentation for time series classification~(TSC). Our review found that Randomized Smoothing performs modestly in TSC, struggling to provide effective assurances on datasets with poor robustness. Therefore, we propose a self-ensemble method to enhance the lower bound of the probability confidence of predicted labels by reducing the variance of classification margins, thereby certifying a larger radius. This approach also addresses the computational overhead issue of Deep Ensemble~(DE) while remaining competitive and, in some cases, outperforming it in terms of robustness. Both theoretical analysis and experimental results validate the effectiveness of our method, demonstrating superior performance in robustness testing compared to baseline approaches.
Previous research has indicated that deep neural network based models for time series classification (TSC) tasks are prone to overfitting. This issue can be mitigated by employing strategies that prevent the model from becoming overly confident in its predictions, such as label smoothing and confidence penalty. Building upon the concept of label smoothing, we propose a novel approach to generate more reliable soft labels, which we refer to as representation soft label smoothing. We apply label smoothing, confidence penalty, and our method representation soft label smoothing to several TSC models and compare their performance with baseline method which only uses hard labels for training. Our results demonstrate that the use of these enhancement techniques yields competitive results compared to the baseline method. Importantly, our method demonstrates strong performance across models with varying structures and complexities.