mlsanityData to 13 Oct 2026

TSGBench: Time Series Generation Benchmark

arXiv 2309.03755 ↗First posted 7 Sep 2023cs.LG cs.AI cs.DBcited by 25

Not on the map. Why?

Abstract (arXiv)

Synthetic Time Series Generation (TSG) is crucial in a range of applications, including data augmentation, anomaly detection, and privacy preservation. Although significant strides have been made in this field, existing methods exhibit three key limitations: (1) They often benchmark against similar model types, constraining a holistic view of performance capabilities. (2) The use of specialized synthetic and private datasets introduces biases and hampers generalizability. (3) Ambiguous evaluation measures, often tied to custom networks or downstream tasks, hinder consistent and fair comparison. To overcome these limitations, we introduce textsfTSGBench, the inaugural Time Series Generation Benchmark, designed for a unified and comprehensive assessment of TSG methods. It comprises three modules: (1) a curated collection of publicly available, real-world datasets tailored for TSG, together with a standardized preprocessing pipeline; (2) a comprehensive evaluation measures suite including vanilla measures, new distance-based assessments, and visualization tools; (3) a pioneering generalization test rooted in Domain Adaptation (DA), compatible with all methods. We have conducted comprehensive experiments using textsfTSGBench across a spectrum of ten real-world datasets from diverse domains, utilizing ten advanced TSG methods and twelve evaluation measures. The results highlight the reliability and efficacy of textsfTSGBench in evaluating TSG methods. Crucially, textsfTSGBench delivers a statistical analysis of the performance rankings of these methods, illuminating their varying performance across different datasets and measures and offering nuanced insights into the effectiveness of each method.

Key facts. Cited by 25 papers in the map (data through 13 Oct 2026). Builds on 45 of its 94 references that are in the map. First posted on arXiv 7 Sep 2023.

Builds on

45 of 94 references.

References · 45

  1. 2017Neural Discrete Representation Learningcited by 4,680
  2. 2018Neural Ordinary Differential Equationscited by 3,750
  3. 2016Density estimation using Real NVPcited by 2,033
  4. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,542
  5. 2014NICE: Non-linear Independent Components Estimationcited by 1,054
  6. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 874
  7. 2018Deep learning for time series classification: a reviewcited by 575
  8. 2014Semi-Supervised Learning with Deep Generative Modelscited by 494
  9. 2018The UCR Time Series Archivecited by 427
  10. 2018The UEA multivariate time series classification archive, 2018cited by 336
  11. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 331
  12. 2019Unsupervised Scalable Representation Learning for Multivariate Time Seriescited by 268
33 more
  1. 2018Adversarial Audio Synthesiscited by 224
  2. 2021How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Modelscited by 194
  3. 2021Neural SDEs as Infinite-Dimensional GANscited by 161
  4. 2021TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generationcited by 141
  5. 2016C-RNN-GAN: Continuous recurrent neural networks with adversarial trainingcited by 132
  6. 2019Quant GANs: Deep Generation of Financial Time Seriescited by 107
  7. 2020Multi-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Datacited by 82
  8. 2020COT-GAN: Generating Sequential Data via Causal Optimal Transportcited by 70
  9. 2018SOM-VAE: Interpretable Discrete Representation Learning on Time Seriescited by 60
  10. 2021Sig-Wasserstein GANs for Time Series Generationcited by 60
  11. 2022Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Versioncited by 59
  12. 2021PSA-GAN: Progressive Self Attention GANs for Synthetic Time Seriescited by 58
  13. 2020Exathlon: A Benchmark for Explainable Anomaly Detection over Time Seriescited by 56
  14. 2020Time Series Domain Adaptation via Sparse Associative Structure Alignmentcited by 51
  15. 2023Vector Quantized Time Series Generation with a Bidirectional Prior Modelcited by 49
  16. 2021AutoCTS: Automated Correlated Time Series Forecasting -- Extended Versioncited by 48
  17. 2022ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Datacited by 45
  18. 2023Causal Recurrent Variational Autoencoder for Medical Time Series Generationcited by 45
  19. 2022A Multifaceted Benchmarking of Synthetic Electronic Health Record Generation Modelscited by 43
  20. 2022GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networkscited by 43
  21. 2022TTS-GAN: A Transformer-based Time-Series Generative Adversarial Networkcited by 41
  22. 2020Modeling Continuous Stochastic Processes with Dynamic Normalizing Flowscited by 37
  23. 2022Deep Latent State Space Models for Time-Series Generationcited by 37
  24. 2020Conditional GAN for timeseries generationcited by 36
  25. 2021Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles -- Extended Versioncited by 35
  26. 2018T-CGAN: Conditional Generative Adversarial Network for Data Augmentation in Noisy Time Series with Irregular Samplingcited by 29
  27. 2021Towards Generating Real-World Time Series Datacited by 26
  28. 2020A Benchmark Study on Time Series Clusteringcited by 25
  29. 2022Generating multivariate time series with COmmon Source CoordInated GAN (COSCI-GAN)cited by 23
  30. 2023Regular Time-series Generation using SGMcited by 23
  31. 2023TSGM: A Flexible Framework for Generative Modeling of Synthetic Time Seriescited by 17
  32. 2022Time-series Transformer Generative Adversarial Networkscited by 10
  33. 2021Conditional Loss and Deep Euler Scheme for Time Series Generationcited by 4

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2023: 3; 2024: 6; 2025: 10; 2026: 6.

25 papers.

Sort:

By area:

  1. 2023Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEscited by 48
  2. 2023Explainable Time Series Anomaly Detection using Masked Latent Generative Modelingcited by 15
  3. 2025Structured Agentic Workflows for Financial Time-Series Modeling with LLMs and Reflective Feedbackcited by 9
  4. 2025Causal Time Series Generation via Diffusion Modelscited by 7
  5. 2024AIGC for Industrial Time Series: From Deep Generative Models to Large Generative Modelscited by 6
  6. 2025Forging Time Series with Language: A Large Language Model Approach to Synthetic Data Generationcited by 6
  7. 2024A Survey of Transformer Enabled Time Series Synthesiscited by 5
  8. 2025WaveStitch: Flexible and Fast Conditional Time Series Generation with Diffusion Modelscited by 4
  9. 2023Masked Generative Modeling with Enhanced Sampling Schemecited by 3
  10. 2025Synthetic Aircraft Trajectory Generation Using Time-Based VQ-VAEcited by 3
  11. 2025TimeWak: Temporal Chained-Hashing Watermark for Time Series Datacited by 3
  12. 2025CTBench: Cryptocurrency Time Series Generation Benchmarkcited by 3
13 more
  1. 2026FinStressTS: A Parametric Synthetic Benchmark for Time-Series Forecasting in Financecited by 2
  2. 2025STEB: In Search of the Best Evaluation Approach for Synthetic Time Seriescited by 1
  3. 2025How to Unlock Time Series Editing? Diffusion-Driven Approach with Multi-Grained Controlcited by 1
  4. 2026E4GEN: Event-level Explainable Extreme-Enhanced Time-series Generationcited by 1
  5. 2024Generating Synthetic Time Series Data for Cyber-Physical Systemscited by 0
  6. 2024SSSD-ECG-nle: New Label Embeddings with Structured State-Space Models for ECG generationcited by 0
  7. 2024Blending Low and High-Level Semantics of Time Series for Better Masked Time Series Generationcited by 0
  8. 2024Multivariate Data Augmentation for Predictive Maintenance using Diffusioncited by 0
  9. 2025PIGPVAE: Physics-Informed Gaussian Process Variational Autoencoderscited by 0
  10. 2026Towards a Unified Generative Model for Scarce Time Series with Domain Expertscited by 0
  11. 2026MIDiff: Tackling Sparsity and Imbalance in Mobile Usage Generation via Multivariate-Imaging Diffusioncited by 0
  12. 2026Monotone-Constrained Diffusion Models for Long-Horizon Production Forecastingcited by 0
  13. 2026DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecastingcited by 0