Effective Series Decomposition and Components Learning for Time Series Generation

TL;DR

This paper introduces STDiffusion, a novel framework combining diffusion models with interpretative series decomposition for more realistic and meaningful multivariate time series generation, demonstrating state-of-the-art results.

Contribution

The paper presents a new diffusion-based approach that explicitly decomposes series into trend and seasonal components, improving interpretability and generation quality.

Findings

Achieves state-of-the-art performance on eight datasets.

Effectively models multi-resolution seasonal components.

Robustly generates long-sequence time series across multiple windows.

Abstract

Time series generation focuses on modeling the underlying data distribution and resampling to produce authentic time series data. Key components, such as trend and seasonality, drive temporal fluctuations, yet many existing approaches fail to employ interpretative decomposition methods, limiting their ability to synthesize meaningful trend and seasonal patterns. To address this gap, we introduce Seasonal-Trend Diffusion (STDiffusion), a novel framework for multivariate time series generation that integrates diffusion probabilistic models with advanced learnable series decomposition techniques, enhancing the interpretability of the generation process. Our approach separates the trend and seasonal learning into distinct blocks: a Multi-Layer Perceptron (MLP) structure captures the trend, while adaptive wavelet distillation facilitates effective multi-resolution learning of seasonal components. This decomposition improves the interpretability of the model on multiple scales. In addition, we designed a comprehensive correction mechanism aimed at ensuring that the generated components exhibit a high degree of internal consistency and preserve meaningful interrelationships with one another. Our empirical studies on eight real-world datasets demonstrate that STDiffusion achieves state-of-the-art performance in time series generation tasks. Furthermore, we extend the model's application to multi-window long-sequence time series generation, which delivered reliable results and highlighted its robustness and versatility.