Time series generation (TSG) studies have mainly focused on the use of Generative Adversarial Networks (GANs) combined with recurrent neural network (RNN) variants. However, the fundamental limitations and challenges of training GANs still remain. In addition, the RNN-family typically has difficulties with temporal consistency between distant timesteps. Motivated by the successes in the image generation (IMG) domain, we propose TimeVQVAE, the first work, to our knowledge, that uses vector quantization (VQ) techniques to address the TSG problem. Moreover, the priors of the discrete latent spaces are learned with bidirectional transformer models that can better capture global temporal consistency. We also propose VQ modeling in a time-frequency domain, separated into low-frequency (LF) and high-frequency (HF). This allows us to retain important characteristics of the time series and, in turn, generate new synthetic signals that are of better quality, with sharper changes in modularity, than its competing TSG methods. Our experimental evaluation is conducted on all datasets from the UCR archive, using well-established metrics in the IMG literature, such as Fr\'echet inception distance and inception scores. Our implementation on GitHub: \url{https://github.com/ML4ITS/TimeVQVAE}.
翻译:时间序列生成(TSG)研究主要侧重于使用General Adversarial Network(GANs)以及经常性神经网络(RNN)变体,然而,培训GAN的基本限制和挑战仍然存在,此外,RNN-家庭通常在遥远的时步之间的时间一致性方面有困难,由于图像生成(IMG)领域的成功,我们提议使用矢量定量技术(VQ)处理TSG问题的首次工作,即Timage VQVAE。此外,离散潜在空间的前身是双向变异器模型学习的,这些模型可以更好地获取全球时间一致性。我们还提议将VQ建模在一个时频域,分为低频(LF)和高频(HFF),这使我们能够保留时间序列的重要特征,并反过来产生比其模块性更明显变化的新的合成信号。我们的实验评价是在UCRR/RUMER4档案的所有数据集上进行,在IMB/FRML4的远程初始实施中,在IMGMA中,在IMA的高级开始中,在IGMI&MLTA中进行。</s>