mlsanityData to 7 Oct 2026

Towards Controllable Time Series Generation

arXiv 2403.03698 ↗First posted 6 Mar 2024cs.LG cs.AI cs.DBcited by 4

Not on the map. Why?

Abstract (arXiv)

Time Series Generation (TSG) has emerged as a pivotal technique in synthesizing data that accurately mirrors real-world time series, becoming indispensable in numerous applications. Despite significant advancements in TSG, its efficacy frequently hinges on having large training datasets. This dependency presents a substantial challenge in data-scarce scenarios, especially when dealing with rare or unique conditions. To confront these challenges, we explore a new problem of Controllable Time Series Generation (CTSG), aiming to produce synthetic time series that can adapt to various external conditions, thereby tackling the data scarcity issue. In this paper, we propose Controllable Time Series (textsfCTS), an innovative VAE-agnostic framework tailored for CTSG. A key feature of textsfCTS is that it decouples the mapping process from standard VAE training, enabling precise learning of a complex interplay between latent features and external conditions. Moreover, we develop a comprehensive evaluation scheme for CTSG. Extensive experiments across three real-world time series datasets showcase textsfCTS's exceptional capabilities in generating high-quality, controllable outputs. This underscores its adeptness in seamlessly integrating latent features with external conditions. Extending textsfCTS to the image domain highlights its remarkable potential for explainability and further reinforces its versatility across different modalities.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 48 of its 95 references that are in the map. First posted on arXiv 6 Mar 2024.

Builds on

48 of 95 references.

References · 48

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2017Neural Discrete Representation Learningcited by 4,650
  4. 2018Neural Ordinary Differential Equationscited by 3,733
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  6. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  7. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  8. 2018Disentangling by Factorisingcited by 614
  9. 2014Semi-Supervised Learning with Deep Generative Modelscited by 494
  10. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
  11. 2019ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernelscited by 336
  12. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 329
36 more
  1. 2017Variational Inference of Disentangled Latent Concepts from Unlabeled Observationscited by 240
  2. 2020Weakly-Supervised Disentanglement Without Compromisescited by 237
  3. 2019Recurrent Independent Mechanismscited by 219
  4. 2020Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learningcited by 219
  5. 2018Isolating Sources of Disentanglement in Variational Autoencoderscited by 167
  6. 2019A Meta-Transfer Objective for Learning to Disentangle Causal Mechanismscited by 158
  7. 2022ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functionscited by 153
  8. 2019On the Fairness of Disentangled Representationscited by 144
  9. 2021TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generationcited by 139
  10. 2016C-RNN-GAN: Continuous recurrent neural networks with adversarial trainingcited by 132
  11. 2015Deep Convolutional Inverse Graphics Networkcited by 121
  12. 2020Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Codingcited by 121
  13. 2019Learning Neural Causal Models from Unknown Interventionscited by 113
  14. 2017Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observationscited by 100
  15. 2020On Disentangled Representations Learned From Correlated Datacited by 94
  16. 2019Weakly Supervised Disentanglement with Guaranteescited by 82
  17. 2016Auxiliary Deep Generative Modelscited by 72
  18. 2017Learning Disentangled Representations with Semi-Supervised Deep Generative Modelscited by 72
  19. 2020CONFIG: Controllable Neural Face Image Generationcited by 61
  20. 2021Sig-Wasserstein GANs for Time Series Generationcited by 60
  21. 2020Dual Contradistinctive Generative Autoencodercited by 58
  22. 2021PSA-GAN: Progressive Self Attention GANs for Synthetic Time Seriescited by 58
  23. 2020Guided Variational Autoencoder for Disentanglement Learningcited by 57
  24. 2023Vector Quantized Time Series Generation with a Bidirectional Prior Modelcited by 49
  25. 2023Causal Recurrent Variational Autoencoder for Medical Time Series Generationcited by 44
  26. 2020Conditional GAN for timeseries generationcited by 36
  27. 2021Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles -- Extended Versioncited by 35
  28. 2020Capturing Label Characteristics in VAEscited by 30
  29. 2021Towards Generating Real-World Time Series Datacited by 26
  30. 2016Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesiscited by 24
  31. 2020Soft-IntroVAE: Analyzing and Improving the Introspective Variational Autoencodercited by 23
  32. 2022Generating multivariate time series with COmmon Source CoordInated GAN (COSCI-GAN)cited by 23
  33. 2014Discovering Hidden Factors of Variation in Deep Networkscited by 21
  34. 2017Disentangled Variational Auto-Encoder for Semi-supervised Learningcited by 17
  35. 2016Nested Mini-Batch K-Meanscited by 5
  36. 2020Adversarial Disentanglement with Grouped Observationscited by 5

Built on by

Cited by year

Citing papers per year: 2025: 4.

4 papers.

  1. 2025BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modelingcited by 18
  2. 2025Causal Time Series Generation via Diffusion Modelscited by 7
  3. 2025CTBench: Cryptocurrency Time Series Generation Benchmarkcited by 3
  4. 2025How to Unlock Time Series Editing? Diffusion-Driven Approach with Multi-Grained Controlcited by 1