DiM-TS: Bridge the Gap between Selective State Space Models and Time Series for Generative Modeling

TL;DR

DiM-TS introduces a novel diffusion-based time series generation model that effectively captures long-range dependencies and complex inter-channel relations, improving realism and property preservation.

Contribution

The paper extends the Mamba state space model with Lag Fusion and Permutation Scanning techniques, culminating in the DiM-TS model for enhanced time series synthesis.

Findings

DiM-TS outperforms existing models in generating realistic time series.

Theoretical analysis shows a unified matrix framework for the proposed variants.

Experiments confirm better preservation of temporal and inter-channel properties.

Abstract

Time series data plays a pivotal role in a wide variety of fields but faces challenges related to privacy concerns. Recently, synthesizing data via diffusion models is viewed as a promising solution. However, existing methods still struggle to capture long-range temporal dependencies and complex channel interrelations. In this research, we aim to utilize the sequence modeling capability of a State Space Model called Mamba to extend its applicability to time series data generation. We firstly analyze the core limitations in State Space Model, namely the lack of consideration for correlated temporal lag and channel permutation. Building upon the insight, we propose Lag Fusion Mamba and Permutation Scanning Mamba, which enhance the model's ability to discern significant patterns during the denoising process. Theoretical analysis reveals that both variants exhibit a unified matrix multiplication framework with the original Mamba, offering a deeper understanding of our method. Finally, we integrate two variants and introduce Diffusion Mamba for Time Series (DiM-TS), a high-quality time series generation model that better preserves the temporal periodicity and inter-channel correlations. Comprehensive experiments on public datasets demonstrate the superiority of DiM-TS in generating realistic time series while preserving diverse properties of data.