Contaminated Multivariate Time-Series Anomaly Detection with Spatio-Temporal Graph Conditional Diffusion Models
On the map: Diffusion models → Flow matching, time series and science
Abstract (arXiv)
Mainstream unsupervised anomaly detection algorithms often excel in academic datasets, yet their real-world performance is restricted due to the controlled experimental conditions involving clean training data. Addressing the challenge of training with noise, a prevalent issue in practical anomaly detection, is frequently overlooked. In a pioneering endeavor, this study delves into the realm of label-level noise within sensory time-series anomaly detection (TSAD). This paper presents a novel and practical end-to-end unsupervised TSAD when the training data is contaminated with anomalies. The introduced approach, called TSAD-C, is devoid of access to abnormality labels during the training phase. TSAD-C encompasses three core modules: a Decontaminator to rectify anomalies (aka noise) present during training, a Long-range Variable Dependency Modeling module to capture long-term intra- and inter-variable dependencies within the decontaminated data that is considered as a surrogate of the pure normal data, and an Anomaly Scoring module to detect anomalies from all types. Our extensive experiments conducted on four reliable and diverse datasets conclusively demonstrate that TSAD-C surpasses existing methodologies, thus establishing a new state-of-the-art in the TSAD field.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 36 of its 62 references that are in the map. First posted on arXiv 24 Aug 2023.
Builds on
36 of 62 references.
Closest ancestors · 5
Same direction, newest first
- 2023Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection14 Jul
- 2023ImDiffusion: Imputed Diffusion Models for Multivariate Time Series Anomaly Detection3 Jul
- 2023On Diffusion Modeling for Anomaly Detection29 May
- 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation7 Jul
- 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting28 Jan
Other references · 31
- 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
- 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
- 2018How Powerful are Graph Neural Networks?cited by 4,393
- 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
- 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 2,022
- 2022Diffusion Models in Vision: A Surveycited by 1,015
- 2020Long Range Arena: A Benchmark for Efficient Transformerscited by 700
- 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 605
- 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 410
- 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 301
- 2022Diffusion Models for Medical Anomaly Detectioncited by 232
- 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 198
19 more
- 2022It's Raw! Audio Generation with State-Space Modelscited by 171
- 2020Multivariate Time-series Anomaly Detection via Graph Attention Networkcited by 167
- 2020Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XLcited by 158
- 2020Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progresscited by 151
- 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
- 2023DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detectioncited by 103
- 2021Towards a Rigorous Evaluation of Time-series Anomaly Detectioncited by 97
- 2018The Temple University Hospital Seizure Detection Corpuscited by 83
- 2021Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysiscited by 76
- 2021A Survey on Graph Structure Learning: Progress and Opportunitiescited by 71
- 2021Neural Contextual Anomaly Detection for Time Seriescited by 43
- 2021Noisy Recurrent Neural Networkscited by 42
- 2022Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Seriescited by 42
- 2019Dreem Open Datasets: Multi-Scored Sleep Datasets to compare Human and Automated sleep stagingcited by 33
- 2022Modeling Multivariate Biosignals With Graph Neural Networks and Structured State Space Modelscited by 29
- 2022Self-Supervised Learning for Anomalous Channel Detection in EEG Graphs: Application to Seizure Analysiscited by 28
- 2022LSTM-Autoencoder based Anomaly Detection for Indoor Air Quality Time Series Datacited by 19
- 2023Graph Anomaly Detection in Time Series: A Surveycited by 18
- 2022Anomaly Detection by Leveraging Incomplete Anomalous Knowledge with Anomaly-Aware Bidirectional GANscited by 11
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 1; 2026: 1.
3 papers.
Similar, not cited
Close in wording, no citation either way
- 2026FirstDiff: One-Step Diffusion-Based Anomaly Detection for Multivariate Time Series via Initial Noise Prediction
- 2026Selective Denoising Diffusion Model for Time Series Anomaly Detection
- 2023Time Series Anomaly Detection using Diffusion-based Models
- 2025Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy
- 2025Physics-Informed Diffusion Models for Unsupervised Anomaly Detection in Multivariate Time Series
- 2025Calibrated Unsupervised Anomaly Detection in Multivariate Time-series using Reinforcement Learning
- 2025AXIS: Explainable Time Series Anomaly Detection with Large Language Models
- 2024Angel or Devil: Discriminating Hard Samples and Anomaly Contaminations for Unsupervised Time Series Anomaly Detection