AVATAR: Adversarial Autoencoders with Autoregressive Refinement for Time Series Generation

TL;DR

AVATAR is a novel framework combining adversarial autoencoders and autoregressive learning to generate realistic time series data, effectively capturing temporal dependencies and improving data augmentation.

Contribution

The paper introduces AVATAR, a new method that integrates supervised and distribution losses with autoencoders for enhanced time series generation.

Findings

Significant improvements in data quality and utility across multiple datasets.

Effective capture of temporal dependencies in generated time series.

Enhanced performance in data augmentation tasks.

Abstract

Data augmentation can significantly enhance the performance of machine learning tasks by addressing data scarcity and improving generalization. However, generating time series data presents unique challenges. A model must not only learn a probability distribution that reflects the real data distribution but also capture the conditional distribution at each time step to preserve the inherent temporal dependencies. To address these challenges, we introduce AVATAR, a framework that combines Adversarial Autoencoders (AAE) with Autoregressive Learning to achieve both objectives. Specifically, our technique integrates the autoencoder with a supervisor and introduces a novel supervised loss to assist the decoder in learning the temporal dynamics of time series data. Additionally, we propose another innovative loss function, termed distribution loss, to guide the encoder in more efficiently aligning the aggregated posterior of the autoencoder's latent representation with a prior Gaussian distribution. Furthermore, our framework employs a joint training mechanism to simultaneously train all networks using a combined loss, thereby fulfilling the dual objectives of time series generation. We evaluate our technique across a variety of time series datasets with diverse characteristics. Our experiments demonstrate significant improvements in both the quality and practical utility of the generated data, as assessed by various qualitative and quantitative metrics.