Time Series Generation

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

1 dataset whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 36 papers with code (87 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
  8 Jun 2017 8 repositories listed Syntology ran 3 of 3 samples · 0 unverified
  We also describe novel evaluation methods for GANs, where we generate a synthetic labelled training dataset, and evaluate on a real test set the performance of a model trained on the synthetic data, and vice-versa.
• Time-series Transformer Generative Adversarial Networks
  23 May 2022 5 repositories listed
  We consider limitations posed specifically on time-series data and present a model that can generate synthetic time-series which can be used in place of real data.
• GRATIS: GeneRAting TIme Series with diverse and controllable characteristics
  7 Mar 2019 5 repositories listed
  The explosion of time series data in recent years has brought a flourish of new time series analysis methods, for forecasting, clustering, classification and other tasks.
• TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation
  15 Nov 2021 3 repositories listed Syntology ran 1 of 6 samples · 5 unverified
  Such interpretability can be highly advantageous in applications requiring transparency of model outputs or where users desire to inject prior knowledge of time-series patterns into the generative model.
• TimEHR: Image-based Time Series Generation for Electronic Health Records
  9 Feb 2024 2 repositories listed
  Time series in Electronic Health Records (EHRs) present unique challenges for generative models, such as irregular sampling, missing values, and high dimensionality.
• Vector Quantized Time Series Generation with a Bidirectional Prior Model
  8 Mar 2023 2 repositories listed Syntology ran 3 of 16 samples · 13 unverified
  Time series generation (TSG) studies have mainly focused on the use of Generative Adversarial Networks (GANs) combined with recurrent neural network (RNN) variants.
• MTSS-GAN: Multivariate Time Series Simulation Generative Adversarial Networks
  26 Jun 2020 2 repositories listed
  MTSS-GAN is a new generative adversarial network (GAN) developed to simulate diverse multivariate time series (MTS) data with finance applications in mind.
• Conditional Sig-Wasserstein GANs for Time Series Generation
  9 Jun 2020 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  The signature of a path is a graded sequence of statistics that provides a universal description for a stream of data, and its expected value characterises the law of the time-series model.
• EEG-GAN: Generative adversarial networks for electroencephalograhic (EEG) brain signals
  5 Jun 2018 2 repositories listed
  Generative adversarial networks (GANs) are recently highly successful in generative applications involving images and start being applied to time series data.
• T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Models
  5 May 2025 1 repository listed
  Text-to-Time Series generation holds significant potential to address challenges such as data sparsity, imbalance, and limited availability of multimodal time series datasets across domains.
• Diffusion Transformers for Tabular Data Time Series Generation
  10 Apr 2025 1 repository listed Syntology ran 2 of 5 samples · 3 unverified · 1 pointer-only (licence)
  Inspired by the recent success of DiTs in image and video generation, we extend this framework to deal with heterogeneous data and variable-length sequences.
• WaveStitch: Flexible and Fast Conditional Time Series Generation with Diffusion Models
  8 Mar 2025 1 repository listed
  By efficiently encoding categorical features, WaveStitch provides a robust and efficient solution for temporal data generation.
• Closing the Gap Between Synthetic and Ground Truth Time Series Distributions via Neural Mapping
  29 Jan 2025 1 repository listed
  In this paper, we introduce Neural Mapper for Vector Quantized Time Series Generator (NM-VQTSG), a novel method aimed at addressing fidelity challenges in vector quantized (VQ) time series generation.
• AVATAR: Adversarial Autoencoders with Autoregressive Refinement for Time Series Generation
  3 Jan 2025 1 repository listed
  Specifically, our technique integrates the autoencoder with a supervisor and introduces a novel supervised loss to assist the decoder in learning the temporal dynamics of time series data.
• Population Aware Diffusion for Time Series Generation
  1 Jan 2025 1 repository listed Syntology ran 6 of 8 samples · 2 unverified · 8 pointer-only (licence)
  We propose Population-aware Diffusion for Time Series (PaD-TS), a new TS generation model that better preserves the population-level properties.
• PATH: A Discrete-sequence Dataset for Evaluating Online Unsupervised Anomaly Detection Approaches for Multivariate Time Series
  21 Nov 2024 1 repository listed
  To cater for both unsupervised and semi-supervised anomaly detection settings, as well as time series generation and forecasting, we make different versions of the dataset available, where training and test subsets are…
• FM-TS: Flow Matching for Time Series Generation
  12 Nov 2024 1 repository listed Syntology ran 9 of 20 samples · 11 unverified · 20 pointer-only (licence)
  FM-TS is more efficient in terms of training and inference.
• SeriesGAN: Time Series Generation via Adversarial and Autoregressive Learning
  28 Oct 2024 1 repository listed
  Current Generative Adversarial Network (GAN)-based approaches for time series generation face challenges such as suboptimal convergence, information loss in embedding spaces, and instability.
• ChronoGAN: Supervised and Embedded Generative Adversarial Networks for Time Series Generation
  21 Sep 2024 1 repository listed Syntology ran 3 of 6 samples · 3 unverified
  This advanced framework integrates the benefits of an Autoencoder-generated embedding space with the adversarial training dynamics of GANs.
• SigDiffusions: Score-Based Diffusion Models for Long Time Series via Log-Signature Embeddings
  14 Jun 2024 1 repository listed Syntology ran 25 of 41 samples · 16 unverified · 9 pointer-only (licence)
  Score-based diffusion models have recently emerged as state-of-the-art generative models for a variety of data modalities.
• Diffusion-TS: Interpretable Diffusion for General Time Series Generation
  4 Mar 2024 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  Denoising diffusion probabilistic models (DDPMs) are becoming the leading paradigm for generative models.
• Time-Transformer: Integrating Local and Global Features for Better Time Series Generation
  18 Dec 2023 1 repository listed
  Experimental results demonstrate that our model can outperform existing state-of-the-art models in 5 out of 6 datasets, specifically on those with data containing both global and local properties.
• Explainable Time Series Anomaly Detection using Masked Latent Generative Modeling
  21 Nov 2023 1 repository listed
  We present a novel time series anomaly detection method that achieves excellent detection accuracy while offering a superior level of explainability.
• Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs
  4 Oct 2023 1 repository listed Syntology ran 6 of 10 samples · 4 unverified · 10 pointer-only (licence)
  In this work, we introduce Koopman VAE (KoVAE), a new generative framework that is based on a novel design for the model prior, and that can be optimized for either regular and irregular training data.
• TSGBench: Time Series Generation Benchmark
  7 Sep 2023 1 repository listed Syntology ran 11 of 14 samples · 3 unverified · 14 pointer-only (licence)
  Synthetic Time Series Generation (TSG) is crucial in a range of applications, including data augmentation, anomaly detection, and privacy preservation.
• Non-adversarial training of Neural SDEs with signature kernel scores
  25 May 2023 1 repository listed
  Neural SDEs are continuous-time generative models for sequential data.
• PCF-GAN: generating sequential data via the characteristic function of measures on the path space
  21 May 2023 1 repository listed
  Generating high-fidelity time series data using generative adversarial networks (GANs) remains a challenging task, as it is difficult to capture the temporal dependence of joint probability distributions induced by…
• Causal Recurrent Variational Autoencoder for Medical Time Series Generation
  16 Jan 2023 1 repository listed Syntology ran 1 of 2 samples · 1 unverified · 2 pointer-only (licence)
  We propose causal recurrent variational autoencoder (CR-VAE), a novel generative model that is able to learn a Granger causal graph from a multivariate time series x and incorporates the underlying causal mechanism into…
• Neural SDEs for Conditional Time Series Generation and the Signature-Wasserstein-1 metric
  3 Jan 2023 1 repository listed
  To overcome this, we propose the use of \textit{Conditional Neural Stochastic Differential Equations}, which have a constant memory cost as a function of depth, being more memory efficient than traditional deep learning…
• Deep Latent State Space Models for Time-Series Generation
  24 Dec 2022 1 repository listed Syntology ran 3 of 3 samples · 0 unverified
  Methods based on ordinary differential equations (ODEs) are widely used to build generative models of time-series.

Syntology lines on 14 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.