Graph-Guided Reconstruction Diffusion for Multivariate Time Series Anomaly Detection

Jinming Yao, Xu Wang, Yudong Zhang, Zhengyang Zhou, Binwu Wang, Yang WangOpenReview 2026 · Submission to ICLR 2026 · Withdrawn · OpenReview

Its authors withdrew this paper, so there is no full text to read or summarize.

Abstract

Time series anomaly detection often faces challenges such as non-stationarity and trendiness. Recently, unsupervised learning methods combined with generative models have shown promising prospects in this field, especially the application of multi-resolution technology in anomaly detection has achieved certain results. However, existing models usually ignore the correlations among different features in time series data and the rich multi-resolutional knowledge contained in the original data. To solve this problem, this paper proposes a new Model, \textbf{G}raph \textbf{G}uided \textbf{R}econstruction \textbf{D}iffusion Model (GGRD). GGRD is an end-to-end unsupervised anomaly detection model based on reconstruction. It adopts overlapping sliding Windows to sample multi-resolution data and integrates the similarity prior in the data into the \textbf{G}raph-\textbf{G}uided \textbf{A}ttention (GGA) mechanism, thereby effectively dealing with complex characteristics such as non-stationarity and cross-variable correlations of time series. The experimental results show that GGRD significantly outperforms the existing methods on multiple real datasets. Code is available at \url{https://anonymous.4open.science/r/GGRD-806F/}.
BibTeX
@misc{yao2026graph,
  author = {Jinming Yao and Xu Wang and Yudong Zhang and Zhengyang Zhou and Binwu Wang and Yang Wang},
  title = {{Graph-Guided Reconstruction Diffusion for Multivariate Time Series Anomaly Detection}},
  year = {2026},
  url = {https://openreview.net/forum?id=mpF6tIx8wz},
  howpublished = {OpenReview},
  note = {Submitted to ICLR 2026},
}

Loading related content...

Figure