arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.01742cs.LGcs.AI
收藏

Diffusion-TS:用于通用时间序列生成的可解释扩散模型

Diffusion-TS: Interpretable Diffusion for General Time Series Generation

Hefei University of Technology(合肥工业大学)

Xinyu Yuan, Yan Qiao

AI总结:

本文提出 Diffusion-TS,一种基于编码器-解码器 Transformer 与解耦时间表示的扩散框架,通过直接重建样本并结合傅里叶损失生成高质量多变量时间序列,可无需改模型即扩展至预测与插补任务,并在多项实验中取得最先进性能。

摘要:

去噪扩散概率模型(DDPMs)正成为生成模型的主流范式,近期在音频合成、时间序列插补和预测方面取得了突破性进展。本文提出 Diffusion-TS,一种新颖的基于扩散的框架,通过使用具有解耦时间表示的编码器-解码器 Transformer 生成高质量的多变量时间序列样本,其中分解技术引导 Diffusion-TS 捕捉时间序列的语义含义,而 Transformer 从含噪模型输入中挖掘详细的序列信息。与现有基于扩散的方法不同,我们训练模型在每个扩散步骤中直接重建样本而非噪声,并结合基于傅里叶的损失项。Diffusion-TS 有望生成同时满足可解释性和真实性的时间序列。此外,研究表明所提出的 Diffusion-TS 可以轻松扩展到条件生成任务,如预测和插补,而无需任何模型更改。这也促使我们进一步探索 Diffusion-TS 在不规则设置下的性能。最后,通过定性和定量实验,结果表明 Diffusion-TS 在各种现实时间序列分析中取得了最先进的结果。

英文摘要:

Denoising diffusion probabilistic models (DDPMs) are becoming the leading paradigm for generative models. It has recently shown breakthroughs in audio synthesis, time series imputation and forecasting. In this paper, we propose Diffusion-TS, a novel diffusion-based framework that generates multivariate time series samples of high quality by using an encoder-decoder transformer with disentangled temporal representations, in which the decomposition technique guides Diffusion-TS to capture the semantic meaning of time series while transformers mine detailed sequential information from the noisy model input. Different from existing diffusion-based approaches, we train the model to directly reconstruct the sample instead of the noise in each diffusion step, combining a Fourier-based loss term. Diffusion-TS is expected to generate time series satisfying both interpretablity and realness. In addition, it is shown that the proposed Diffusion-TS can be easily extended to conditional generation tasks, such as forecasting and imputation, without any model changes. This also motivates us to further explore the performance of Diffusion-TS under irregular settings. Finally, through qualitative and quantitative experiments, results show that Diffusion-TS achieves the state-of-the-art results on various realistic analyses of time series.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑