Conditional GAN for timeseries generation (original) (raw)
Related papers
A Spectral Enabled GAN for Time Series Data Generation
ArXiv, 2021
Time dependent data is a main source of information in today's data driven world. Generating this type of data though has shown its challenges and made it an interesting research area in the field of generative machine learning. One such approach was that by Smith et al. who developed Time Series Generative Adversarial Network (TSGAN) which showed promising performance in generating time dependent data and the ability of few shot generation though being flawed in certain aspects of training and learning. This paper looks to improve on the results from TSGAN and address those flaws by unifying the training of the independent networks in TSGAN and creating a dependency both in training and learning. This improvement, called unified TSGAN (uTSGAN) was tested and comapred both quantitatively and qualitatively to its predecessor on 70 benchmark time series data sets used in the community. uTSGAN showed to outperform TSGAN in 80\% of the data sets by the same number of training epochs...
PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series
2021
Realistic synthetic time series data of sufficient length enables practical applications in time series modeling tasks, such as forecasting, but remains a challenge. In this paper we present PSA-GAN, a generative adversarial network (GAN) that generates long time series samples of high quality using progressive growing of GANs and self-attention. We show that PSA-GAN can be used to reduce the error in two downstream forecasting tasks over baselines that only use real data. We also introduce a Frechet-Inception Distancelike score, Context-FID, assessing the quality of synthetic time series samples. In our downstream tasks, we find that the lowest scoring models correspond to the best-performing ones. Therefore, Context-FID could be a useful tool to develop time series GAN models.
Multivariate Time-Series Data Generation in Generative Adversarial Networks
Time-series data often arises during the monitoring and evaluation of ongoing industrial processes. Time series forecasting requires accurate data modelling through the description of inherent structures such as trend, cycle, and seasonality by collecting and modeling stochastically the historical data points of a time series. In this paper, we are concerned with industrial time series data that is limited and not readily available for accurate machine learning tasks, e.g., online fraud and network intrusion data. In this scenario, modeling of time series can be achieved through generative modeling activities in deep learning. Then, abundant temporal data can be generated and used in different ways to achieve application-level forecasts and predictions. We focus on the use of Generative Adversarial Networks (GANs) to model and generate limited real-world time-series data. We discover that this is a relatively new research domain with research trends generally focusing on employing r...
Time-series Generative Adversarial Networks
2019
A good generative model for time-series data should preserve temporal dynamics, in the sense that new sequences respect the original relationships between variables across time. Existing methods that bring generative adversarial networks (GANs) into the sequential setting do not adequately attend to the temporal correlations unique to time-series data. At the same time, supervised models for sequence prediction - which allow finer control over network dynamics - are inherently deterministic. We propose a novel framework for generating realistic time-series data that combines the flexibility of the unsupervised paradigm with the control afforded by supervised training. Through a learned embedding space jointly optimized with both supervised and adversarial objectives, we encourage the network to adhere to the dynamics of the training data during sampling. Empirically, we evaluate the ability of our method to generate realistic samples using a variety of real and synthetic time-series...
TTS-GAN: A Transformer-based Time-Series Generative Adversarial Network
ArXiv, 2022
Signal measurements appearing in the form of time series are one of the most common types of data used in medical machine learning applications. However, such datasets are often small, making the training of deep neural network architectures ineffective. For time-series, the suite of data augmentation tricks we can use to expand the size of the dataset is limited by the need to maintain the basic properties of the signal. Data generated by a Generative Adversarial Network (GAN) can be utilized as another data augmentation tool. RNN-based GANs suffer from the fact that they cannot effectively model long sequences of data points with irregular temporal relations. To tackle these problems, we introduce TTS-GAN, a transformer-based GAN which can successfully generate realistic synthetic time-series data sequences of arbitrary length, similar to the real ones. Both the generator and discriminator networks of the GAN model are built using a pure transformer encoder architecture. We use vi...
One-shot time series generation using Wasserstein Generative Adversarial Networks
Econometrics is tasked with estimating causal effect. To measure the ability of a model to capture causal effect, econometric researchers often conduct Monte Carlo studies to assess model performance. However, Monte Carlo studies limit the credibility of research because of the freedom a researcher has in specifying the design. Generative adversarial networks, or GANs, are a class of generative models that can be used to generate data that mimic a realworld dataset. Replacing Monte Carlo simulations with artificial data provided by GANs limits the freedom of researchers in simulation design. In this thesis, we attempt to apply (conditional) Wasserstein GANs to generate time series. We find that, (i) when provided with enough data, a WGAN can learn the ARMA(1,1) DGP with fixed parameters; (ii) a conditional WGAN can generate ARMA(1,1) with various parameter estimates, but we are unable to precisely control the type of ARMA (1,1) generated; and (iii) using only a single time series example with a trained embedder, we generate diverse time series with similar dynamics, again without precise control.
Traditionally, time series data augmentation has primarily focused on improving the architecture of Generative Adversarial Network (GAN), with the aim of closely matching the original data distribution while also preserving the dynamic behavior of the original data. However, even state-of-the-art GAN models like TimeGAN fall short in preserving the temporal dynamics present in the original time series due to the absence of first-order difference information. To address this limitation, this study proposes a novel process for generating multivariate time series data. The proposed process comprises four essential modules: a) the GAN module for generating multivariate time series data, b) the sampling module for preserving the first-order difference distribution, c) the smoothing module for refining the generated data, and d) an evaluation module using the Kolmogorov-Smirnov Test (KS-test) and Hilbert-Schmidt Independence Criterion (HSIC), along with other metrics to test the synthetic...
Multivariate Time Series Synthesis Using Generative Adversarial Networks
Proceedings of the ACM/SPEC International Conference on Performance Engineering, 2021
Figure 1: From left to right, top to bottom, the training process of our GAN network is depicted. The generated data is plotted as a density chart throughout the training process, showing how the network learns to reflect the fidelity of the original data.
ArXiv, 2018
In this paper we propose a data augmentation method for time series with irregular sampling, Time-Conditional Generative Adversarial Network (T-CGAN). Our approach is based on Conditional Generative Adversarial Networks (CGAN), where the generative step is implemented by a deconvolutional NN and the discriminative step by a convolutional NN. Both the generator and the discriminator are conditioned on the sampling timestamps, to learn the hidden relationship between data and timestamps, and consequently to generate new time series. We evaluate our model with synthetic and real-world datasets. For the synthetic data, we compare the performance of a classifier trained with T-CGAN-generated data, against the performance of the same classifier trained on the original data. Results show that classifiers trained on T-CGAN-generated data perform the same as classifiers trained on real data, even with very short time series and small training sets. For the real world datasets, we compare our...
If You Like It, GAN It. Probabilistic Multivariate Times Series Forecast With GAN
2021
The contribution of this paper is two-fold. First, we present ProbCast—a novel probabilistic model for multivariate time-series forecasting. We employ a conditional GAN framework to train our model with adversarial training. Second, we propose a framework that lets us transform a deterministic model into a probabilistic one with improved performance. The motivation of the framework is to either transform existing highly accurate point forecast models to their probabilistic counterparts or to train GANs stably by selecting the architecture of GAN’s component carefully and efficiently. We conduct experiments over two publicly available datasets—an electricity consumption dataset and an exchange-rate dataset. The results of the experiments demonstrate the remarkable performance of our model as well as the successful application of our proposed framework.