A Unified Contrastive-Generative Framework for Time Series Classification

• URL: http://arxiv.org/abs/2508.09451v1
• Date: Wed, 13 Aug 2025 03:09:14 GMT
• Title: A Unified Contrastive-Generative Framework for Time Series Classification
• Abstract summary: We propose a Contrastive Generative Time series framework (CoGenT)<n>It overcomes contrastive learning's sensitivity to high intra-class similarity in temporal data while reducing generative methods' dependence on large datasets.<n>The results show consistent improvements, with up to 59.2% and 14.27% F1 gains over standalone SimCLR and MAE, respectively.
• Score: 7.712601563682029
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Self-supervised learning (SSL) for multivariate time series mainly includes two paradigms: contrastive methods that excel at instance discrimination and generative approaches that model data distributions. While effective individually, their complementary potential remains unexplored. We propose a Contrastive Generative Time series framework (CoGenT), the first framework to unify these paradigms through joint contrastive-generative optimization. CoGenT addresses fundamental limitations of both approaches: it overcomes contrastive learning's sensitivity to high intra-class similarity in temporal data while reducing generative methods' dependence on large datasets. We evaluate CoGenT on six diverse time series datasets. The results show consistent improvements, with up to 59.2% and 14.27% F1 gains over standalone SimCLR and MAE, respectively. Our analysis reveals that the hybrid objective preserves discriminative power while acquiring generative robustness. These findings establish a foundation for hybrid SSL in temporal domains. We will release the code shortly.

Related papers

• Empowering Cross-Domain Sequential Recommendation with Hybrid Tokenization and Serial-Parallel Decoding [63.74998371740272]
  Cross-domain sequential recommendation (CDSR) aims to model users' dynamic interest transitions and sequential patterns across multiple domains.<n>We propose GenCDSR, an effective and efficient generative framework for CDSR.<n>We show that GenCDSR achieves an average accuracy improvement of 1.5 percent and an average inference latency reduction of 85.1 percent compared with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-07-21T08:01:15Z)
• Preserving Temporal Dynamics in Time Series Generation [0.2099922236065961]
  Time-series data augmentation plays a crucial role in regression-oriented forecasting tasks.<n>Existing approaches primarily focus on matching marginal data distributions.<n>We propose a model-agnostic Markov Chain Monte Carlo framework to mitigate distribution shift and preserve temporal dynamics.
  arXiv  Detail & Related papers  (2026-04-29T20:32:45Z)
• TimeMar: Multi-Scale Autoregressive Modeling for Unconditional Time Series Generation [11.455232661227313]
  We propose a structure-disentangled multiscale generation framework for time series.<n>Our approach encodes sequences into discrete tokens at multiple temporal resolutions.<n>We show that our approach produces higher-quality time series than existing methods.
  arXiv  Detail & Related papers  (2026-01-16T11:00:05Z)
• TFEC: Multivariate Time-Series Clustering via Temporal-Frequency Enhanced Contrastive Learning [22.300584288382012]
  This paper proposes a Temporal-Frequency Enhanced Contrastive (TFEC) learning framework.<n>To preserve temporal structure while generating low-distortion representations, a temporal-frequency Co-EnHancement (CoEH) mechanism is introduced.<n>Experiments on six real-world benchmark datasets demonstrate TFEC's superiority, achieving 4.48% average NMI gains over SOTA methods.
  arXiv  Detail & Related papers  (2026-01-12T13:59:27Z)
• Segmentation over Complexity: Evaluating Ensemble and Hybrid Approaches for Anomaly Detection in Industrial Time Series [36.94429692322632]
  We evaluate the impact of change point-derived statistical features, clustering-based substructure representations, and hybrid learning strategies on detection performance.<n>The ensemble achieved an AUC-ROC of 0.976, F1-score of 0.41, and 100% early detection within the defined time window.
  arXiv  Detail & Related papers  (2025-10-30T05:39:44Z)
• Modest-Align: Data-Efficient Alignment for Vision-Language Models [67.48633659305592]
  Cross-modal alignment models often suffer from overconfidence and degraded performance when operating in resource-constrained settings.<n>We propose Modest-Align, a lightweight alignment framework designed for robustness and efficiency.<n>Our method offers a practical and scalable solution for cross-modal alignment in real-world, low-resource scenarios.
  arXiv  Detail & Related papers  (2025-10-24T16:11:10Z)
• WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training [64.0932926819307]
  We present Warmup-Stable and Merge (WSM), a framework that establishes a formal connection between learning rate decay and model merging.<n>WSM provides a unified theoretical foundation for emulating various decay strategies.<n>Our framework consistently outperforms the widely-adopted Warmup-Stable-Decay (WSD) approach across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-07-23T16:02:06Z)
• FCPCA: Fuzzy clustering of high-dimensional time series based on common principal component analysis [11.138320457692288]
  This work introduces a novel fuzzy clustering approach based on common principal component analysis.<n>We show that our proposed clustering method outperforms several existing approaches in the literature.<n>An interesting application involving brain signals from different drivers recorded from a simulated driving experiment illustrates the potential of the approach.
  arXiv  Detail & Related papers  (2025-05-12T06:59:17Z)
• Two-stage hybrid models for enhancing forecasting accuracy on heterogeneous time series [0.9281671380673306]
  A forecasting model trained on multiple time series is referred to as a global time series model (tsGM)<n>Benefits of tsGMs may not always be realised if the given set of time series is heterogeneous.
  arXiv  Detail & Related papers  (2025-02-12T17:39:02Z)
• Hybrid Ensemble Deep Graph Temporal Clustering for Spatiotemporal Data [0.37083047471478225]
  We propose a hybrid ensemble graph clustering (HEDGTC) method for multivariate temporal data analysis. HEDGTC adopts a dual consensus approach to address noise and misclassification from traditional clustering. When evaluated on three real-world datasets, HEDGTC outperforms state-of-the-art ensemble clustering models.
  arXiv  Detail & Related papers  (2024-09-19T09:14:10Z)
• GCC: Generative Calibration Clustering [55.44944397168619]
  We propose a novel Generative Clustering (GCC) method to incorporate feature learning and augmentation into clustering procedure. First, we develop a discrimirative feature alignment mechanism to discover intrinsic relationship across real and generated samples. Second, we design a self-supervised metric learning to generate more reliable cluster assignment.
  arXiv  Detail & Related papers  (2024-04-14T01:51:11Z)
• Time-series Generation by Contrastive Imitation [87.51882102248395]
  We study a generative framework that seeks to combine the strengths of both: Motivated by a moment-matching objective to mitigate compounding error, we optimize a local (but forward-looking) transition policy. At inference, the learned policy serves as the generator for iterative sampling, and the learned energy serves as a trajectory-level measure for evaluating sample quality.
  arXiv  Detail & Related papers  (2023-11-02T16:45:25Z)
• Robust Detection of Lead-Lag Relationships in Lagged Multi-Factor Models [61.10851158749843]
  Key insights can be obtained by discovering lead-lag relationships inherent in the data. We develop a clustering-driven methodology for robust detection of lead-lag relationships in lagged multi-factor models.
  arXiv  Detail & Related papers  (2023-05-11T10:30:35Z)
• GraphLearner: Graph Node Clustering with Fully Learnable Augmentation [76.63963385662426]
  Contrastive deep graph clustering (CDGC) leverages the power of contrastive learning to group nodes into different clusters. We propose a Graph Node Clustering with Fully Learnable Augmentation, termed GraphLearner. It introduces learnable augmentors to generate high-quality and task-specific augmented samples for CDGC.
  arXiv  Detail & Related papers  (2022-12-07T10:19:39Z)
• Cluster-and-Conquer: A Framework For Time-Series Forecasting [94.63501563413725]
  We propose a three-stage framework for forecasting high-dimensional time-series data. Our framework is highly general, allowing for any time-series forecasting and clustering method to be used in each step. When instantiated with simple linear autoregressive models, we are able to achieve state-of-the-art results on several benchmark datasets.
  arXiv  Detail & Related papers  (2021-10-26T20:41:19Z)
• Minority Oversampling for Imbalanced Time Series Classification [7.695093197007146]
  This paper proposes a structure preserving Oversampling method to combat the High-dimensional Imbalanced Time-series classification. Experimental results on several publicly available time-series datasets demonstrate the superiority of OHIT against the state-of-the-art oversampling algorithms.
  arXiv  Detail & Related papers  (2020-04-14T09:20:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.