来自今天的爱可可AI前沿推介

[LG] Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement

Y Li, X Lu, Y Wang, D Dou
[Baidu Research & Zhejiang University]

基于扩散、去噪和解缠的生成式时间序列预测

要点:

  1. 提出一种双向变分自编码器(BVAE)，采用扩散、去噪和解缠机制，用于时间序列预测；
  2. 将多尺度去噪分数匹配调整并集成到扩散过程中，以确保生成的序列朝着真实目标移动；
  3. 以多变量方式处理潜变量，并在最小化总相关性上进行解缠，以提高预测的可解释性和稳定性。

一句话总结:
采用扩散、去噪和解缠机制的双向变分自编码器(BVAE) D3VAE 可用于时间序列预测并取得高精度。

摘要：
时间序列预测是一项广泛探索的任务，在许多应用中都非常重要。然而，现实世界的时间序列数据通常记录在短时间内，这导致深度模型与有限而含噪的时间序列之间存在巨大差距。本文提出通过生成建模解决时间序列预测问题，提出一种采用扩散、去噪和解缠机制的双向变分自编码器(BVAE)，即 D3VAE。具体的，提出了一种耦合扩散概率模型，以在不增加延迟不确定性的情况下增加时间序列数据，用BVAE实现更易于操作的推理过程。为了确保生成的序列朝着真实目标移动，进一步提出将多尺度去噪分数匹配调整并集成到时间序列预测的扩散过程中。此外，为了提高预测的可解释性和稳定性，以多变量的方式处理潜变量，并在最小化总相关性之上解开它们。对合成和现实世界数据的广泛实验表明，D3VAE以 显著的收益优于竞争算法。

Time series forecasting has been a widely explored task of great importance in many applications. However, it is common that real-world time series data are recorded in a short time period, which results in a big gap between the deep model and the limited and noisy time series. In this work, we propose to address the time series forecasting problem with generative modeling and propose a bidirectional variational auto-encoder (BVAE) equipped with diffusion, denoise, and disentanglement, namely D3VAE. Specifically, a coupled diffusion probabilistic model is proposed to augment the time series data without increasing the aleatoric uncertainty and implement a more tractable inference process with BVAE. To ensure the generated series move toward the true target, we further propose to adapt and integrate the multiscale denoising score matching into the diffusion process for time series forecasting. In addition, to enhance the interpretability and stability of the prediction, we treat the latent variable in a multivariate manner and disentangle them on top of minimizing total correlation. Extensive experiments on synthetic and real-world data show that D3VAE outperforms competitive algorithms with remarkable margins. Our implementation is available at this https URL.

论文链接：https://arxiv.org/abs/2301.03028
图片
图片
图片
图片

内容中包含的图片若涉及版权问题，请及时与我们联系删除