Vector Quantized Time Series Generation with a Bidirectional Prior Model

2023/03/08 by Dae-Soo Lee, Lee, Daesoo, Sara Malacarne +3 · 10 citations
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Time Series Analysis and Forecasting

paper · pdf · doi:10.48550/arxiv.2303.04743

openalex publication_date 2023/03/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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 Fréchet inception distance and inception scores. Our implementation on GitHub: \urlhttps://github.com/ML4ITS/TimeVQVAE.

Cited by

• Temporal-Visual Semantic Alignment: A Unified Architecture for Transferring Spatial Priors from Vision Models to Zero-Shot Temporal Tasks
• Learning to Land Anywhere: Transferable Generative Models for Aircraft Trajectories
• Learning Reconfigurable Representations for Multimodal Federated Learning with Missing Data
• Forecasting-based Biomedical Time-series Data Synthesis for Open Data and Robust AI
• CTBench: Cryptocurrency Time Series Generation Benchmark
• DualSG: A Dual-Stream Explicit Semantic-Guided Multivariate Time Series Forecasting Framework
• How to Unlock Time Series Editing? Diffusion-Driven Approach with Multi-Grained Control
• PIGPVAE: Physics-Informed Gaussian Process Variational Autoencoders
• Forging Time Series with Language: A Large Language Model Approach to Synthetic Data Generation
• Generating Realistic Multi-Beat ECG Signals

Related

• Closing the Gap Between Synthetic and Ground Truth Time Series Distributions via Neural Mapping
• Blending Low and High-Level Semantics of Time Series for Better Masked Time Series Generation
• Transformer-based conditional generative adversarial network for multivariate time series generation
• ChronoGAN: Supervised and Embedded Generative Adversarial Networks for Time Series Generation
• Leveraging Image-based Generative Adversarial Networks for Time Series Generation