Time Weaver: A Conditional Time Series Generation Model

• URL: http://arxiv.org/abs/2403.02682v2
• Date: Wed, 29 Oct 2025 23:22:45 GMT
• Title: Time Weaver: A Conditional Time Series Generation Model
• Abstract summary: We introduce TIME WEAVER, a novel diffusion-based model for time series generation.<n>We show that TIME WEAVER outperforms state-of-the-art benchmarks on real-world energy, medical, air quality, and traffic datasets.
• Score: 15.762169911963783
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Imagine generating a city's electricity demand pattern based on weather, the presence of an electric vehicle, and location, which could be used for capacity planning during a winter freeze. Such real-world time series are often enriched with paired heterogeneous contextual metadata (e.g., weather and location). Current approaches to time series generation often ignore this paired metadata. Additionally, the heterogeneity in metadata poses several practical challenges in adapting existing conditional generation approaches from the image, audio, and video domains to the time series domain. To address this gap, we introduce TIME WEAVER, a novel diffusion-based model that leverages the heterogeneous metadata in the form of categorical, continuous, and even time-variant variables to significantly improve time series generation. Additionally, we show that naive extensions of standard evaluation metrics from the image to the time series domain are insufficient. These metrics do not penalize conditional generation approaches for their poor specificity in reproducing the metadata-specific features in the generated time series. Thus, we innovate a novel evaluation metric that accurately captures the specificity of conditional generation and the realism of the generated time series. We show that TIME WEAVER outperforms state-of-the-art benchmarks, such as Generative Adversarial Networks (GANs), by up to 30% in downstream classification tasks on real-world energy, medical, air quality, and traffic datasets.

Related papers

• Towards a Unified Generative Model for Scarce Time Series with Domain Experts [14.03756371866814]
  TimeMoDE is a novel framework that integrates Diffusion Transformers with Mixture-of-Experts to exploit time series generation under data scarcity.<n>It is pre-trained on a large-scale collection of multi-domain datasets to extract domain-agnostic temporal representations.<n>Extensive experiments demonstrate that TimeMoDE outperforms existing methods under diverse low-data settings.
  arXiv  Detail & Related papers  (2026-06-13T07:41:42Z)
• 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)
• Time-Aware Prior Fitted Networks for Zero-Shot Forecasting with Exogenous Variables [59.37476887007663]
  We develop ApolloPFN, a prior-data fitted network (PFN) that is time-aware (unlike prior PFNs)<n>Our design introduces two major advances: (i) a synthetic data generation procedure tailored to resolve the failure modes that arise when PFNs are applied to time series; and (ii) time-aware architectural modifications that embed inductive biases needed to exploit the time series context.
  arXiv  Detail & Related papers  (2026-03-16T18:33:23Z)
• MEMTS: Internalizing Domain Knowledge via Parameterized Memory for Retrieval-Free Domain Adaptation of Time Series Foundation Models [51.506429027626005]
  Memory for Time Series (MEMTS) is a lightweight and plug-and-play method for retrieval-free domain adaptation in time series forecasting.<n>Key component of MEMTS is a Knowledge Persistence Module (KPM), which internalizes domain-specific temporal dynamics.<n>This paradigm shift enables MEMTS to achieve accurate domain adaptation with constant-time inference and near-zero latency.
  arXiv  Detail & Related papers  (2026-02-14T14:00:06Z)
• 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)
• Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach [7.631288333466648]
  We conduct the first large-scale study evaluating leading generative models in data-scarce settings.<n>We propose a unified diffusion-based generative framework that can synthesize high-fidelity time series using just a few examples.
  arXiv  Detail & Related papers  (2025-05-26T18:39:04Z)
• CENTS: Generating synthetic electricity consumption time series for rare and unseen scenarios [4.997673761305336]
  We propose a method for creating high-fidelity electricity consumption time series data for rare and unseen context variables.<n>Our results highlight the efficacy of the proposed method in generating realistic household-level electricity consumption data.
  arXiv  Detail & Related papers  (2025-01-24T11:52:52Z)
• Recurrent Neural Goodness-of-Fit Test for Time Series [8.22915954499148]
  Time series data are crucial across diverse domains such as finance and healthcare. Traditional evaluation metrics fall short due to the temporal dependencies and potential high dimensionality of the features. We propose the REcurrent NeurAL (RENAL) Goodness-of-Fit test, a novel and statistically rigorous framework for evaluating generative time series models.
  arXiv  Detail & Related papers  (2024-10-17T19:32:25Z)
• Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts [103.725112190618]
  This paper introduces Moirai-MoE, using a single input/output projection layer while delegating the modeling of diverse time series patterns to the sparse mixture of experts. Extensive experiments on 39 datasets demonstrate the superiority of Moirai-MoE over existing foundation models in both in-distribution and zero-shot scenarios.
  arXiv  Detail & Related papers  (2024-10-14T13:01:11Z)
• TimeBridge: Better Diffusion Prior Design with Bridge Models for Time Series Generation [3.2066708654182743]
  Time series generation is widely used in real-world applications such as simulation, data augmentation, and hypothesis testing.<n> diffusion models have emerged as the de facto approach to time series generation, enabling diverse synthesis scenarios.<n>We propose TimeBridge, a framework that flexibly synthesizes time series data by using diffusion bridges to learn paths between a chosen prior and the data distribution.
  arXiv  Detail & Related papers  (2024-08-13T06:47:59Z)
• TimeLDM: Latent Diffusion Model for Unconditional Time Series Generation [2.4454605633840143]
  Time series generation is a crucial research topic in the area of decision-making systems. Recent approaches focus on learning in the data space to model time series information. We propose TimeLDM, a novel latent diffusion model for high-quality time series generation.
  arXiv  Detail & Related papers  (2024-07-05T01:47:20Z)
• Discrete-state Continuous-time Diffusion for Graph Generation [46.626952802292074]
  Diffusion generative models have been applied to graph generation tasks. We formulate the graph diffusion generation in a discrete-state continuous-time setting. Our proposed model shows competitive empirical performance against state-of-the-art graph generation solutions.
  arXiv  Detail & Related papers  (2024-05-19T00:09:42Z)
• A Survey on Diffusion Models for Time Series and Spatio-Temporal Data [92.1255811066468]
  We review the use of diffusion models in time series and S-temporal data, categorizing them by model, task type, data modality, and practical application domain. We categorize diffusion models into unconditioned and conditioned types discuss time series and S-temporal data separately. Our survey covers their application extensively in various fields including healthcare, recommendation, climate, energy, audio, and transportation.
  arXiv  Detail & Related papers  (2024-04-29T17:19:40Z)
• Rethinking Urban Mobility Prediction: A Super-Multivariate Time Series Forecasting Approach [71.67506068703314]
  Long-term urban mobility predictions play a crucial role in the effective management of urban facilities and services. Traditionally, urban mobility data has been structured as videos, treating longitude and latitude as fundamental pixels. In our research, we introduce a fresh perspective on urban mobility prediction. Instead of oversimplifying urban mobility data as traditional video data, we regard it as a complex time series.
  arXiv  Detail & Related papers  (2023-12-04T07:39:05Z)
• Instructed Diffuser with Temporal Condition Guidance for Offline Reinforcement Learning [71.24316734338501]
  We propose an effective temporally-conditional diffusion model coined Temporally-Composable diffuser (TCD) TCD extracts temporal information from interaction sequences and explicitly guides generation with temporal conditions. Our method reaches or matches the best performance compared with prior SOTA baselines.
  arXiv  Detail & Related papers  (2023-06-08T02:12:26Z)
• Towards Diverse and Coherent Augmentation for Time-Series Forecasting [22.213927377926804]
  Time-series data augmentations mitigate the issue of insufficient training data for deep learning models. We propose to combine Spectral and Time Augmentation for generating more diverse and coherent samples. Experiments on five real-world time-series datasets demonstrate that STAug outperforms the base models without data augmentation.
  arXiv  Detail & Related papers  (2023-03-24T19:40:34Z)
• Regular Time-series Generation using SGM [12.181761518950044]
  We propose a conditional score network for the time-series generation domain. We also derive the loss function between the score matching and the denoising score matching in the time-series generation domain. Finally, we achieve state-of-the-art results on real-world datasets in terms of sampling diversity and quality.
  arXiv  Detail & Related papers  (2023-01-20T11:34:12Z)
• HyperTime: Implicit Neural Representation for Time Series [131.57172578210256]
  Implicit neural representations (INRs) have recently emerged as a powerful tool that provides an accurate and resolution-independent encoding of data. In this paper, we analyze the representation of time series using INRs, comparing different activation functions in terms of reconstruction accuracy and training convergence speed. We propose a hypernetwork architecture that leverages INRs to learn a compressed latent representation of an entire time series dataset.
  arXiv  Detail & Related papers  (2022-08-11T14:05:51Z)
• Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version [37.09531298150374]
  Traffic series forecasting is challenging due to complex time series patterns for the same time series patterns may vary across time, where, for example, there exist periods across a day showing stronger temporal correlations. Such-temporal models employ a shared parameter space irrespective of the time locations and the time periods and they assume that the temporal correlations are similar across locations and do not always hold across time which may not always be the case. We propose a framework that aims at turning ICD-temporal aware models to encode sub-temporal models.
  arXiv  Detail & Related papers  (2022-03-29T16:44:56Z)
• Novel Features for Time Series Analysis: A Complex Networks Approach [62.997667081978825]
  Time series data are ubiquitous in several domains as climate, economics and health care. Recent conceptual approach relies on time series mapping to complex networks. Network analysis can be used to characterize different types of time series.
  arXiv  Detail & Related papers  (2021-10-11T13:46:28Z)

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.