Abstract
Generative adversarial networks should produce synthetic data that fits the underlying distribution of the data being modeled. For real-valued time series data, this implies the need to simultaneously capture the static distribution of the data, but also the full temporal distribution of the data for any potential time horizon. This temporal element produces a more complex problem that can potentially leave current solutions under-constrained, unstable during training, or prone to varying degrees of mode collapse. In FETSGAN, entire sequences are translated directly to the generator’s sampling space using a seq2seq style adversarial autoencoder, where adversarial training is used to match the training distribution in both the feature space and the lower-dimensional sampling space. This additional constraint provides a loose assurance that the temporal distribution of the synthetic samples will not collapse. In addition, the First Above Threshold operator is introduced to supplement the reconstruction of encoded sequences, which improves training stability and the overall quality of the synthetic data being generated. These novel contributions demonstrate a significant improvement to the current state of the art for adversarial learners in qualitative measures of temporal similarity and quantitative predictive ability of data generated through FETSGAN.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
All the data used for experimentation were publicly available and contain no sensitive or personal information of any kind. No original datasets were produced through this research. All datasets are either provided through citation or provided directly at the linked repository.
References
Esteban C, Hyland SL, Rätsch G (2017) Real-valued (Medical) time series generation with recurrent conditional GANs
Mogren O (2016) C-RNN-GAN: continuous recurrent neural networks with adversarial training
Makhzani A, Shlens J, Jaitly N, Goodfellow I, Frey B (2016) Adversarial autoencoders
Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks
Yoon J, Jarrett D, van der Schaar M (2019) Time-series generative adversarial networks. In: Advances in neural information processing systems, vol. 32. Curran Associates Inc.,
Bengio S, Vinyals O, Jaitly N, Shazeer N (2015) Scheduled sampling for sequence prediction with recurrent neural networks
Lamb A, Goyal A, Zhang Y, Zhang S, Courville A, Bengio Y (2016) Professor forcing: a new algorithm for training recurrent networks
Chung J, Gulcehre C, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling
Arjovsky M, Chintala S, Bottou L (2017) Wasserstein GAN
Fekri MN, Ghosh AM, Grolinger K (2020) Generating energy data for machine learning with recurrent generative adversarial networks. Energies 13(1):130
Xu T, Wenliang LK, Munn M, Acciaio B (2020) COT-GAN: generating sequential data via causal optimal transport. In: Advances in neural information processing systems, vol. 33. Curran Associates Inc., pp. 8798–8809
Jarrett D, Bica I, van der Schaar M (2021) Time-series generation by contrastive imitation. In: Advances in neural information processing systems, vol. 34. Curran Associates Inc., pp. 28 968–28 982
Coletta A, Gopalakrishnan S, Borrajo D, Vyetrenko S (2023) On the constrained time-series generation problem. Advances in Neural Information Processing Systems 36:61048–61059
Dash S, Yale A, Guyon I, Bennett KP (2020) Medical time-series data generation using generative adversarial networks. In: Michalowski M, Moskovitch R (Eds.) Artificial intelligence in medicine, ser. Lecture Notes in Computer Science. Springer International Publishing, Cham, pp. 382–391
Li H, Yu S, Principe J (2023) Causal recurrent variational autoencoder for medical time series generation. In: Proceedings of the AAAI conference on artificial intelligence, vol. 37(7), pp. 8562–8570
Chattoraj S, Pratiher S, Pratiher S, Konik H (2021) Improving stability of adversarial Li-ion cell usage data generation using generative latent space modelling. In: ICASSP 2021—2021 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 8047–8051
Fochesato M, Khayatian F, Lima DF, Nagy Z (2022) On the use of conditional TimeGAN to enhance the robustness of a reinforcement learning agent in the building domain. In: Proceedings of the 9th ACM international conference on systems for energy-efficient buildings, cities, and transportation, ser. BuildSys ’22. Association for Computing Machinery, New York, pp. 208–217
Adib E, Fernandez AS, Afghah F, Prevost JJ (2023) Synthetic ECG signal generation using probabilistic diffusion models. IEEE Access 11:75818–75828
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, ukasz Kaiser Ł, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, vol. 30. Curran Associates Inc
Ray PP (2023) ChatGPT: a comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope. Internet Things Cyber-Phys Syst 3:121–154
Lyu X, Hueser M, Hyland SL, Zerveas G, Raetsch G (2018) Improving clinical predictions through unsupervised time series representation learning
Dai AM, Le QV (2015) Semi-supervised sequence learning
Bianchi FM, Livi L, Mikalsen KØ, Kampffmeyer M, Jenssen R (2019) Learning representations for multivariate time series with missing data using temporal kernelized autoencoders
Kingma DP, Welling M (2013) Auto-encoding variational Bayes
Tolstikhin I, Bousquet O, Gelly S, Schoelkopf B (2019) Wasserstein auto-encoders
Liu M-Y, Breuel T, Kautz J (2017) Unsupervised image-to-image translation networks. In: Advances in neural information processing systems, vol. 30. Curran Associates Inc.,
Zhu J-Y, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp. 2223–2232
Mao X, Li Q, Xie H, Lau RYK, Wang Z, Smolley SP (2017) Least squares generative adversarial networks
Miyato T, Kataoka T, Koyama M, Yoshida Y (2018) Spectral normalization for generative adversarial networks
Xiang S, Li H (2017) On the effects of batch and weight normalization in generative adversarial networks
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization, arXiv preprint arXiv:1412.6980
Candanedo LM, Feldheim V, Deramaix D (2017) Data driven prediction models of energy use of appliances in a low-energy house. Energy Build 140:81–97
Hogue J (2018) Traffic data from mn department of transportation, weather data from openweathermap
van der Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9(86):2579–2605
Funding
Funding for this work was partially provided by the Collaborative Sciences Center for Road Safety (CSCRS), as well as the University of Tennessee, Knoxville.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no known conflict of interest in the content of this manuscript.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Beck, J., Chakraborty, S. Fully embedded time series generative adversarial networks. Neural Comput & Applic (2024). https://doi.org/10.1007/s00521-024-09825-5
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s00521-024-09825-5