The DOI matches its Crossref record; 61 of the 61 references it cites were found in a registry or an index.
DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection
Open accessAbstract
Time series anomaly detection is critical for a wide range of applications. It aims to identify deviant samples from the normal sample distribution in time series. The most fundamental challenge for this task is to learn a representation map that enables effective discrimination of anomalies. Reconstruction-based methods still dominate, but the representation learning with anomalies might hurt the performance with its large abnormal loss. On the other hand, contrastive learning aims to find a representation that can clearly distinguish any instance from the others, which can bring a more natural and promising representation for time series anomaly detection. In this paper, we propose DCdetector, a multi-scale dual attention contrastive representation learning model. DCdetector utilizes a novel dual attention asymmetric design to create the permutated environment and pure contrastive loss to guide the learning process, thus learning a permutation invariant representation with superior discrimination abilities. Extensive experiments show that DCdetector achieves state-of-the-art results on multiple time series anomaly detection benchmark datasets. Code is publicly available at https://github.com/DAMO-DI-ML/KDD2023-DCdetector.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Furthermore, the latest research shows that contrastive-based methods, such as Skip-CPC [113] and Dcdetector [126], have achieved the best performance on four datasets.”
From Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects (2024) · cites this paper as [126]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Recently, DCdetector [126] proposes a dual attention contrastive representation framework for time series anomaly detection. The in-patch and patch-wise representations are designed to gain two views of the input samples, as normal samples behave differently from abnormal ones in such two views.”
From Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects (2024) · cites this paper as [126]
The cited source says what the claim attributes to it.
In the citing paper
“Note that in time series anomaly detection task, the adjustment strategy is widely adopted: if a time point in a certain successive abnormal segment is detected, all anomalies in this abnormal segment are viewed to be correctly detected [81], [126], [163].”
From Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects (2024) · cites this paper as [126]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Advances in neural information processing systems 7
(1996) · Computers & Mathematics with Applications · doi:10.1016/s0898-1221(96)90463-0 · Cited by 14,759
Momentum Contrast for Unsupervised Visual Representation Learning
He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00975 · Cited by 13,347
LOF: identifying density-based local outliers
Breunig, M. M., Kriegel, H.-P., Ng, R. T., & Sander, J. (2000) · Proceedings of the 2000 ACM SIGMOD international conference on Management of data · doi:10.1145/342009.335388 · Cited by 4,149
Exploring Simple Siamese Representation Learning
Chen, X., & He, K. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01549 · Cited by 3,725
Unsupervised Feature Learning via Non-parametric Instance Discrimination
Wu, Z., Xiong, Y., Yu, S. X., & Lin, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00393 · Cited by 3,664
Box, G. E. P., & Pierce, D. A. (1970) · Journal of the American Statistical Association · doi:10.2307/2284333 · Cited by 3,212
DeepAR: Probabilistic forecasting with autoregressive recurrent networks
Salinas, D., Flunkert, V., Gasthaus, J. A., & Januschowski, T. (2019) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2019.07.001 · Cited by 3,094
Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network
Su, Y., Zhao, Y., Niu, C., Liu, R., Sun, W., & Pei, D. (2019) · Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3292500.3330672 · Cited by 1,804
Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding
Hundman, K., Constantinou, V., Laporte, C., Colwell, I., & Soderstrom, T. (2018) · Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3219819.3219845 · Cited by 1,771
Research works printed but not linked: 27
- Archana Anandakrishnan , Senthil Kumar , Alexander Statnikov , Tanveer Faruquie , and Di Xu . 2018 . Anomaly detection in finance: editors' introduction . In KDD 2017 Workshop on Anomaly Detection in Finance. PMLR, 1--7. Archana Anandakrishnan, Senthil Kumar, Alexander Statnikov, Tanveer Faruquie, and Di Xu. 2018. Anomaly detection in finance: editors' introduction. In KDD 2017 Workshop on Anomaly Detection in Finance. PMLR, 1--7.
- OD Anderson . 1976. Time-Series . 2 nd edn. OD Anderson. 1976. Time-Series. 2nd edn.
- 10.1080/01621459.1970.10481180 · DOI
- David Campos , Tung Kieu , Chenjuan Guo , Feiteng Huang , Kai Zheng , Bin Yang , and Christian S Jensen . 2021. Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles-Extended Version. arXiv preprint arXiv:2111.11108 ( 2021 ). David Campos, Tung Kieu, Chenjuan Guo, Feiteng Huang, Kai Zheng, Bin Yang, and Christian S Jensen. 2021. Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles-Extended Version. arXiv preprint arXiv:2111.11108 (2021). · arXiv
- Mathilde Caron , Ishan Misra , Julien Mairal , Priya Goyal , Piotr Bojanowski , and Armand Joulin . 2020. Unsupervised learning of visual features by contrasting cluster assignments. Advances in neural information processing systems , Vol. 33 ( 2020 ), 9912--9924. Mathilde Caron, Ishan Misra, Julien Mairal, Priya Goyal, Piotr Bojanowski, and Armand Joulin. 2020. Unsupervised learning of visual features by contrasting cluster assignments. Advances in neural information processing systems, Vol. 33 (2020), 9912--9924.
- Ting Chen , Simon Kornblith , Mohammad Norouzi , and Geoffrey Hinton . 2020 . A simple framework for contrastive learning of visual representations . In International conference on machine learning. PMLR, 1597--1607 . Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607.
- Ailin Deng and Bryan Hooi . 2021 a. Graph Neural Network-Based Anomaly Detection in Multivariate Time Series. In AAAI Conference on Artificial Intelligence. Ailin Deng and Bryan Hooi. 2021a. Graph Neural Network-Based Anomaly Detection in Multivariate Time Series. In AAAI Conference on Artificial Intelligence.
- Jingkun Gao , Xiaomin Song , Qingsong Wen , Pichao Wang , Liang Sun , and Huan Xu . 2020 . RobustTAD: Robust time series anomaly detection via decomposition and convolutional neural networks . KDD Workshop MileTS (2020). Jingkun Gao, Xiaomin Song, Qingsong Wen, Pichao Wang, Liang Sun, and Huan Xu. 2020. RobustTAD: Robust time series anomaly detection via decomposition and convolutional neural networks. KDD Workshop MileTS (2020).
- Jean-Bastien Grill , Florian Strub , Florent Altché , Corentin Tallec , Pierre Richemond , Elena Buchatskaya , Carl Doersch , Bernardo Avila Pires , Zhaohan Guo, Mohammad Gheshlaghi Azar, et al. 2020 . Bootstrap your own latent-a new approach to self-supervised learning. Advances in neural information processing systems, Vol. 33 (2020), 21271--21284. Jean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhaohan Guo, Mohammad Gheshlaghi Azar, et al. 2020. Bootstrap your own latent-a new approach to self-supervised learning. Advances in neural information processing systems, Vol. 33 (2020), 21271--21284.
- Neha Kant and Manish Mahajan . 2019. Time-series outlier detection using enhanced k-means in combination with pso algorithm . In Engineering Vibration, Communication and Information Processing: ICoEVCI 2018 , India. Springer , 363--373. Neha Kant and Manish Mahajan. 2019. Time-series outlier detection using enhanced k-means in combination with pso algorithm. In Engineering Vibration, Communication and Information Processing: ICoEVCI 2018, India. Springer, 363--373.
- Paweł Karczmarek , Adam Kiersztyn , Witold Pedrycz , and Ebru Al. 2020. K-Means-based isolation forest. Knowledge-based systems , Vol. 195 ( 2020 ), 105659. Paweł Karczmarek, Adam Kiersztyn, Witold Pedrycz, and Ebru Al. 2020. K-Means-based isolation forest. Knowledge-based systems, Vol. 195 (2020), 105659.
- Eamonn Keogh , Dutta Roy Taposh , U Naik , and A Agrawal . 2021 . Multi-dataset Time-Series Anomaly Detection Competition. In ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. https://compete. hexagonml. com/practice/competition/39 . Eamonn Keogh, Dutta Roy Taposh, U Naik, and A Agrawal. 2021. Multi-dataset Time-Series Anomaly Detection Competition. In ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. https://compete. hexagonml. com/practice/competition/39.
- Taesung Kim , Jinhee Kim , Yunwon Tae , Cheonbok Park , Jang-Ho Choi , and Jaegul Choo . 2021 . Reversible instance normalization for accurate time-series forecasting against distribution shift . In International Conference on Learning Representations. Taesung Kim, Jinhee Kim, Yunwon Tae, Cheonbok Park, Jang-Ho Choi, and Jaegul Choo. 2021. Reversible instance normalization for accurate time-series forecasting against distribution shift. In International Conference on Learning Representations.
- Kwei-Herng Lai , Daochen Zha , Junjie Xu , Yue Zhao , Guanchu Wang , and Xia Hu . 2021 . Revisiting time series outlier detection: Definitions and benchmarks . In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1). Kwei-Herng Lai, Daochen Zha, Junjie Xu, Yue Zhao, Guanchu Wang, and Xia Hu. 2021. Revisiting time series outlier detection: Definitions and benchmarks. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1).
- Shiyang Li , Xiaoyong Jin , Yao Xuan , Xiyou Zhou , Wenhu Chen , Yu-Xiang Wang , and Xifeng Yan . 2019b. Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting. Advances in neural information processing systems , Vol. 32 ( 2019 ). Shiyang Li, Xiaoyong Jin, Yao Xuan, Xiyou Zhou, Wenhu Chen, Yu-Xiang Wang, and Xifeng Yan. 2019b. Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting. Advances in neural information processing systems, Vol. 32 (2019).
- Fei Tony Liu , Kai Ming Ting, and Zhi-Hua Zhou . 2008 . Isolation forest. In 2008 eighth ieee international conference on data mining. IEEE , 413--422. Fei Tony Liu, Kai Ming Ting, and Zhi-Hua Zhou. 2008. Isolation forest. In 2008 eighth ieee international conference on data mining. IEEE, 413--422.
- Steffen Moritz Frederik Rehbach Sowmya Chandrasekaran Margarita Rebolledo and Thomas Bartz-Beielstein. 2018. GECCO Industrial Challenge 2018 Dataset: a water quality dataset for the ?Internet of Things: Online Anomaly Detection for Drinking Water Quality" competition at the Genetic and Evolutionary Computation Conference 2018 Kyoto Japan (2018). Steffen Moritz Frederik Rehbach Sowmya Chandrasekaran Margarita Rebolledo and Thomas Bartz-Beielstein. 2018. GECCO Industrial Challenge 2018 Dataset: a water quality dataset for the ?Internet of Things: Online Anomaly Detection for Drinking Water Quality" competition at the Genetic and Evolutionary Computation Conference 2018 Kyoto Japan (2018).
- Adam Paszke , Sam Gross , Francisco Massa , Adam Lerer , James Bradbury , Gregory Chanan , Trevor Killeen , Zeming Lin , Natalia Gimelshein , Luca Antiga , 2019 . Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems , Vol. 32 (2019). Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019).
- Mathias Perslev , Michael Jensen , Sune Darkner , Poul Jørgen Jennum , and Christian Igel . 2019 . U-time: A fully convolutional network for time series segmentation applied to sleep staging . Advances in Neural Information Processing Systems , Vol. 32 (2019). Mathias Perslev, Michael Jensen, Sune Darkner, Poul Jørgen Jennum, and Christian Igel. 2019. U-time: A fully convolutional network for time series segmentation applied to sleep staging. Advances in Neural Information Processing Systems, Vol. 32 (2019).
- Lukas Ruff , Robert Vandermeulen , Nico Goernitz , Lucas Deecke , Shoaib Ahmed Siddiqui , Alexander Binder , Emmanuel Müller , and Marius Kloft . 2018 . Deep one-class classification . In International conference on machine learning. PMLR, 4393--4402 . Lukas Ruff, Robert Vandermeulen, Nico Goernitz, Lucas Deecke, Shoaib Ahmed Siddiqui, Alexander Binder, Emmanuel Müller, and Marius Kloft. 2018. Deep one-class classification. In International conference on machine learning. PMLR, 4393--4402.
- David MJ Tax and Robert PW Duin . 2004. Support vector data description. Machine learning , Vol. 54 , 1 ( 2004 ), 45--66. David MJ Tax and Robert PW Duin. 2004. Support vector data description. Machine learning, Vol. 54, 1 (2004), 45--66.
- Jiehui Xu , Haixu Wu , Jianmin Wang , and Mingsheng Long . 2021. Anomaly transformer: Time series anomaly detection with association discrepancy. arXiv preprint arXiv:2110.02642 ( 2021 ). Jiehui Xu, Haixu Wu, Jianmin Wang, and Mingsheng Long. 2021. Anomaly transformer: Time series anomaly detection with association discrepancy. arXiv preprint arXiv:2110.02642 (2021). · arXiv
- Chin-Chia Michael Yeh , Yan Zhu , Liudmila Ulanova , Nurjahan Begum , Yifei Ding , Hoang Anh Dau , Diego Furtado Silva , Abdullah Mueen , and Eamonn Keogh . 2016 . Matrix profile I: all pairs similarity joins for time series: a unifying view that includes motifs, discords and shapelets . In 2016 IEEE 16th international conference on data mining (ICDM). Ieee, 1317--1322 . Chin-Chia Michael Yeh, Yan Zhu, Liudmila Ulanova, Nurjahan Begum, Yifei Ding, Hoang Anh Dau, Diego Furtado Silva, Abdullah Mueen, and Eamonn Keogh. 2016. Matrix profile I: all pairs similarity joins for time series: a unifying view that includes motifs, discords and shapelets. In 2016 IEEE 16th international conference on data mining (ICDM). Ieee, 1317--1322.
- Zahra Zamanzadeh Darban , Geoffrey I Webb , Shirui Pan , Charu C Aggarwal , and Mahsa Salehi . 2022. Deep Learning for Time Series Anomaly Detection: A Survey. arXiv e-prints ( 2022 ), arXiv-2211. Zahra Zamanzadeh Darban, Geoffrey I Webb, Shirui Pan, Charu C Aggarwal, and Mahsa Salehi. 2022. Deep Learning for Time Series Anomaly Detection: A Survey. arXiv e-prints (2022), arXiv-2211.
- Chaoning Zhang , Kang Zhang , Chenshuang Zhang , Trung X Pham , Chang D Yoo , and In So Kweon . 2022 b. How does SimSiam avoid collapse without negative samples? a unified understanding with self-supervised contrastive learning . Proceedings of International Conference on Learning Representations (ICLR) (2022). Chaoning Zhang, Kang Zhang, Chenshuang Zhang, Trung X Pham, Chang D Yoo, and In So Kweon. 2022b. How does SimSiam avoid collapse without negative samples? a unified understanding with self-supervised contrastive learning. Proceedings of International Conference on Learning Representations (ICLR) (2022).
- 10.1109/ICDM50108.2020.00093 · DOI
- Bo Zong , Qi Song , Martin Renqiang Min , Wei Cheng , Cristian Lumezanu , Daeki Cho , and Haifeng Chen . 2018 . Deep autoencoding gaussian mixture model for unsupervised anomaly detection . In International conference on learning representations. Bo Zong, Qi Song, Martin Renqiang Min, Wei Cheng, Cristian Lumezanu, Daeki Cho, and Haifeng Chen. 2018. Deep autoencoding gaussian mixture model for unsupervised anomaly detection. In International conference on learning representations.
Cited by
Sorted by citations
Items 301–387 of 387
EnsDiffAD: Ensemble Diffusion Models for Multivariate Time Series Anomaly Detection
Ma, Q., Li, Y., Bai, M., Wang, X., Guo, S., Gu, Y., & Yu, G. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2026.3708334
“Despite recent advances, most MTSAD methods, such as DCdetector [35] and TranAD [8], primarily focus on temporal dependencies while overlooking complex inter-variable correlations.”
ATOM: Adaptive Temporal Omniview Mixer for Lightweight Multivariate Time-Series Anomaly Detection
Jia, X., Peng, W., Xun, P., Zhao, B., & Shen, C. (2026) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2026.3702381
“Early autoencoder-and Generative Adversarial Network (GAN)-based detectors, such as USAD [10], improve nonlinear modeling, while Transformer-based methods, such as anomaly Transformer and DCdetector [11], [12], further enhancetemporaldependencemodeling.”
D-RGATDiff: Unified Spatiotemporal Diffusion for IoT Network Time Series Anomaly Detection
Zou, C., Ruan, Y., Yang, L. T., Deng, X., Liu, S., Wang, S. Y., & Hou, R. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3709053
Wu, Z., Wang, X., Chen, Z., & Kong, X. (2026) · International Conference on Computing, Networks and Internet of Things (CNIOT) · doi:10.1109/cniot69547.2026.11581998
“…the reconstruction-based models: LSTM-VAE [12], BeatGAN [13], OmniAnomaly [16], Anomaly Transformer (AT) [18], TransDe [15] and DCdetector [19]; the autoregression-based models: LSTM [10], and CL-MPPCA [20]; the density-estimation models: LOF [1] and MMPCACD [21]; the clustering-based…”
Xu, G., Ye, Z., Huang, X., Liu, L., Wu, C., & Mumtaz, S. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3710784
“Recent advances in Transformer-based MTSAD have shown strong potential because self-attention can capture long-range temporal dependencies and complex cross-variable interactions more e ff ectively than many earlier recurrent or convolutional alternatives [9], [10], [11], [12], [13], [14], [15].”
Wang, Y., Lu, J., Zhou, B., Zhang, Y., Li, X., Yuan, J., & Wang, L. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08690-4
Time-frequency hybrid decomposition for multivariate time series anomaly detection
Shi, D., Zhang, T., Duan, Y., & Sun, L. G. (2026) · Evolving Systems · doi:10.1007/s12530-026-09856-4
“The time-domain meth-ods encompass: AutoEncoder (AE) (Sakurada and Yairi 2014), Anomaly Transformer (AT) (Xu et al. 2021), DCde - tector (DC) (Yang et al. 2023), ModernTCN (MTCN) (Luo and Wang 2024), NLinear (NL) (Zeng et al. 2023), DLinear (DL) (Zeng et al. 2023), ITransformer (IT) (Liu et al.…”
Self-citationZhang, X., & Lu, X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3438-7_13
Adaptive Time-Frequency Modeling with Energy Priors for Multivariate Time Series Anomaly Detection
Chen, F., & Pan, W. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3384-7_7
Huang, J., Li, W., Guo, X., Jiang, Y., Jiang, Y., Wang, H., Wan, J., & Zheng, M. (2026) · Agronomy · doi:10.3390/agronomy16141349
DualCrossAD: Interpretable DualCross-Attention for Time Series Anomaly Detection
Zhang, Z., & Guo, G. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3394-6_13
Tang, M., Guan, L., & Duan, L. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3450-9_19
Mamba-based Contrastive Learning for Industrial Multivariate Time-Series Anomaly Detection
Guan, Y., & Ji, K. (2026) · International Conference on Algorithms, Software Engineering and Network Security (ASENS) · doi:10.1109/asens69964.2026.11605334
“Specifically, the baselines include TS2Vec [18], TimesNet [19], THOC [20], Anomaly Transformer [8], and DCdetector [12].”
Unsupervised Representation Learning for Time Series Anomaly Detection: Overview and new Trends
Hamida, O. I., Boudane, F., & Berrichi, A. (2026) · International Conference on Pattern Analysis and Intelligent Systems (PAIS) · doi:10.1109/pais69842.2026.11605406
“A prominent example of this evolution is DCdetector [44], which introduces a Dual Attention Contrastive structure.”
AI-Based Detection of Financially Incorrect States in Visually Stable Web Dashboards
Afanasieva, T. (2026) · IEEE International Conference on AI and Data Analytics (ICAD) · doi:10.1109/icad69378.2026.11608603
“Methods such as dual-attention contrastive frameworks [9] and self-supervised contrastive techniques applied to attributed networks [10] improve separation of normal versus anomalous patterns in multivariate sequences.”
Knowledge Graph–Augmented Reasoning for Robust Multi-modal Document Attack Detection
Li, T. F., Zhang, X., Tian, J., Feng, Y., Li, Y. F., Ma, Z., & Ma, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3015-0_15
Hyperbolic adaptive spatial-aware multivariate time series anomaly detection
Han, J., Huo, X., Xiao, Y., Ye, Z., Zheng, Y., Zhao, H., Sun, M., & Liu, Z. (2026) · Nature Communications · doi:10.1038/s41467-026-75881-1
MCL: Mamba-Based Contrastive Learning method for coal gangue identification
Qiu, H., Zhang, Z., Zhang, B., Yang, S., Yao, N., & Liu, H. (2026) · International Journal of Coal Preparation and Utilization · doi:10.1080/19392699.2026.2708066
Wensheng, Y., Ke, G., & Chen, J. (2026) · WSEAS TRANSACTIONS ON BUSINESS AND ECONOMICS · doi:10.37394/23207.2026.23.97
Kim, J. I., Lee, J., Kim, J., Heo, J., Jeong, J., & Kim, S. B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31666-0_15
CALAD: Channel-Aware Contrastive Learning for Multivariate Time Series Anomaly Detection
Hong, J., & Hur, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31404-8_38
WassDRO-AD: Distributionally Robust Anomaly Detection for Multivariate IoT Data Streams
Liu, X., Liu, R., & Yang, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-34377-2_15
Self-citationZero-Shot Wireless Sensor Anomaly Detection via Global-Local Temporal Representation Learning
Cui, L., Sun, Y., Zhang, C., Liang, Y., Wang, W., & Xu, P. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3718880
“Representation-based methods learn robust feature representations for downstream tasks, with notable examples including TF-C [18] and DCDetector [19].”
Self-citationWang, Y., Han, F., Li, K., Liu, S., Chen, T., & Peng, Z. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3817943
Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detection
Tang, Q., Dai, C., Ma, W., Wu, Y., Zhou, H., Zhang, T., Li, H., & Zhang, D. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818108
Foundation Models for Time Series Analysis: Concepts, Methodologies, and Applications
Liang, Y., Wen, H., Jiang, Y., Jin, M., Song, D., Wu, M., Pan, S., & Wen, Q. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3816446
Self-citationSEA-FGT: Frequency-Guided Transformer with Semantic Expert Augment for Time Series Anomaly Detection
Huang, W. X., Wang, Z., Huang, Y., Liu, J., & Ouyang, X. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3817823
Sun, L., Zhang, S., Xue, X., Li, L., Zhou, H., & Li, J. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818034
Self-citationLu, Y., Gao, Y., Lan, T., Yang, Y., He, W., Wang, M., & Zhang, C. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3817912
Self-citationXie, F., Zhong, H., Chen, Q., Qiu, K., Lu, W., Wang, X., & Wang, X. (2026) · International Conference on Electronic Engineering and Informatics (EEI) · doi:10.1109/eei70303.2026.11640497
“Transformer-based detectors have advanced multivariate time-series anomaly detection [6]– [8], and time-series foundation models are now being explored for anomaly detection [9].”
Zhang, B., Kieu, T., Qiu, X., Guo, C., Hu, J., Zhou, A., Jensen, C. S., & Yang, B. (2026) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde65706.2026.00074
“(12) AnomalyTrans [75] models prior associations and series associations to capture the association discrepancies; (13) DCdetector [76] detects time series anomalies using robust representations based on contrastive learning.”
InfluentialEditor: Multi-Resolution Cleaning of Multivariate Time Series Via Detect-Localize-Repair
Li, C., Ma, C., Yu, X., Li, C., & Meng, X. (2026) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde65706.2026.00249
Zong, W. (2026) · International Conference on Artificial Intelligence and Electromechanical Automation (AIEA) · doi:10.1109/aiea70743.2026.11632327
“Public benchmarks such as SMAP, MSL, SMD, and PSM have made this setting a common testbed for unsupervised anomaly detection [1]-[3].”
IA-AD: a contrastive framework with Inception-Attention for time series anomaly detection
Lin, L., Liang, Z., Li, Y., Qiu, J., & Zhong, Q. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08790-1
Du, C., Hu, Z., Hu, J., & Chen, S. (2026) · Batteries · doi:10.3390/batteries12080308
“…locate abnormal temporal patterns [10], TranAD introduces transformer-based self-conditioning for multivariate anomaly detection [25], DCdetector uses dual attention with contrastive learning [11], and TimesNet converts one-dimensional series into two-dimensional temporal variation patterns [12].”
Multi-view feature fusion and contrastive representation learning for pipeline leak detection
Meng, X., & GaizhiGuo (2026) · Complex & Intelligent Systems · doi:10.1007/s40747-026-02404-2
CHAIN: Long-Context History-Supervised Multivariate Time Series Anomaly Detection
Jun, E., & Yim, J. (2026) · IEEE Access · doi:10.1109/access.2026.3725308
“…Anomaly Transformer [16], TranAD [49], AD-NEv [58], AD-NEv++ [59] Forecasting+Reconstruction-based: MTAD-GAT [14] Representation-based: DCdetector [22], TimesNet [23], CARLA [24] D. EVALUATION METRICS For evaluation measures, we chose Precision, Recall, and F1-Score suitable for unbalanced data.”
InfluentialTFCD-AD: Temporal-Frequency Coupling Discrepancy for Multivariate Time Series Anomaly Detection
Huang, C., Zhang, X., Zhang, Z., Yin, T., & Yan, M. L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37654-1_12
Ilyin, E. V., & Sidorkina, I. (2026) · Computational nanotechnology · doi:10.33693/2313-223x-2026-13-2-162-175
Xiao, J., Liu, Q., Ji, C., & Chen, K. (2026) · International Conference on Computer Information and Big Data Applications (CIBDA) · doi:10.1145/3813822.3813923
“Inspired by this, patching has also been applied to anomaly detection: Dcdetector [2] constructs patch-level representations for each time series, adopts a dual-branch attention mechanism for feature extraction, and further strengthens representation learning with a contrastive learning strategy.”
Learning to detect anomalies with adaptive feature graphs and contrast in multivariate time series
Liu, W., Sun, D., & Yang, H. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.105117
Liu, X., 尚援朝, Luo, W., Zhao, G., & Gai, T. (2026) · IEEE International Conference on Smart Internet of Things (SmartIoT) · doi:10.1109/smartiot70864.2026.00017
“Existing methods include classical time-series similarity approaches [5], statistical and machine-learning outlier-detection methods [6–8], deep learning models [12,21,22], and time-series foundation models [23].”
A dual-path multi-view framework for deployment-oriented time series anomaly detection
Jin, L., Liu, Y., Jiang, Q., & Liang, K. (2026) · Cluster Computing · doi:10.1007/s10586-026-06534-7
“…UCR [29 ] is a benchmark collection of univariate time series datasets widely used for evaluating time series classification and anomaly detection meth - ods, and its enhanced version UCR_AUG [30] is used to evaluate the generalization ability of the model after introducing perturbations.”
Dynamic Trend Perception for Fine-Grained Unmanned Aerial Vehicle Anomaly Detection in Flight Data
Yin, Y., Yin, Y., Wei, Y., Su, Q., & Li, J. (2026) · ENGINEERING Information Technology & Electronic Engineering · doi:10.1631/eng.itee.2026.0060
Mohamed, A., Dtissibe, F. Y., Djedouboum, A. C., Njoya, A. N., & Mohamadou, A. (2026) · EAI/Springer Innovations in Communication and Computing · doi:10.1007/978-3-032-08820-8_7
Teng, S., & Gao, X. (2026) · Sensors · doi:10.3390/s26185751
“Temporal one-class and contrastive methods provide further alternatives to direct reconstruction [13,32].”
Zhu, H., Yang, B., & Yang, D. (2026) · International Conference on Computer Information Science and Application Technology (CISAT) · doi:10.1109/cisat71030.2026.11682668
“…detectors score by reconstruction error or attention patterns: the Anomaly Transformer (AT) [6] uses an association-discrepancy minimax criterion, TranAD [9] adds self-conditioning and adversarial training, and DCdetector [10] replaces reconstruction with dual-attention contrastive learning.”
Zhang, D., Chen, S., & Xiang, W. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38404-1_34
Intelligent Anomaly Understanding and Response for Water Cyber-Physical Systems
Yang, Z., Shi, Q., Lin, Y.-Z., Lei, T., Satam, P., & Shao, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38404-1_48
Zhang, Y. (2026) · Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence (DEAI) · doi:10.1145/3837873.3838048
“…in compliance environments where expert labeling is costly and time-sensitive; prior work on Raha demonstrated effective error detection with as few as 10 labeled tuples, and our ablation experiments confirmed that detection performance plateaued beyond approximately 150 samples for this [ 9 ] .”
Zhou, Y., HAYASHI, N., & Inuiguchi, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7471096
Bimad: bidirectional Mamba-based anomaly detection for multivariate time series
Huang, J., Yang, L., & Liu, H. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05719-2
“…[23], and CL-MPPCA [24]; Reconstruction-based : Deep-SVDD [25], DAGMM [26], BeatGAN [15], OmniAnomaly [9], and InterFusion [27]; Prediction-based : VAR [14], LSTM [5], and LSTM-VAE [28]; and SOTA Transformers/Advanced : ITAD [29], THOC [30], Anomaly Transformer [10], DCdetector [11], and MAAT [19].”
Reliability constrained diffusion modeling for high-noise defect detection using ACFM
Zhang, Z., Liu, W., Zhao, H., Sun, L., Yang, W., & Yuan, X. (2026) · NDT & E International · doi:10.1016/j.ndteint.2026.103870
Self-citationSun, M. (2026) · International Conference on Artificial Intelligence, Internet of Things and Cloud Computing Technology (AIoTC) · doi:10.1109/aiotc71250.2026.11689298
Long, J., Yan, X., Hong, J., Luo, Y., & Qi, Q. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-01284-3
“Other studies have explored contrastive representation learning, frequency-domain reconstruction, and Kolmogorov – Arnold networks for robust anomaly detection (Wang et al. 2024; Yang et al. 2023; Zhou et al. 2025).”
Huang, Z., Li, Z., Wu, Y., & Xiao, C. (2026) · IEEE Access · doi:10.1109/access.2026.3734098
“Mainstream multivariate time-series anomaly detection methods include TranAD [28], Anomaly Transformer [27], and DCdetector [29].”
Chae, M.-S., & Park, T.-H. (2026) · Sensors · doi:10.3390/s26196037
AMAD: AutoMasked Attention for unsupervised multivariate time series anomaly detection
Huang, T., Li, G., Li, Y., & Zhang, W. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.117110
Guo, W., Su, N., Jiang, G., & Wang, K. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08885-9
“More recent studies have introduced Transformers and graph neural networks to better capture long-range temporal dependencies and inter-variable interactions, with representative models including InterFusion [22], GDN [23], GTA [24], TranAD [25], Anomaly Transformer [26], and DCdetector [27].”
Zhang, Z. (2026) · International Conference on Mechanical, Electronics and Electrical and Automation Control (METMS) · doi:10.1109/metms70800.2026.11706329
“TCAD differs from recent related work in kind rather than degree: contrastive detectors refine the representation but keep coarse thresholding [13]; aero-engine bearing studies address component-level classification with labeled samples [14]; and LSTM-based models on the same compressor degradation…”
Deng, Y. (2026) · International Conference on Advanced Algorithms and Neural Networks (AANN) · doi:10.1109/aann71145.2026.11709150
“Recent methods extend this family with dual-attention contrastive representations [21], degradation-based self-supervision [22], and time-frequency consistency [23].”
Cao, H., & Ma, J. (2026) · International Conference on Advanced Algorithms and Neural Networks (AANN) · doi:10.1109/aann71145.2026.11709358
Hydraulic System Anomaly Detection Using a Spatial-Graph-Enhanced Sub-Adjacent Transformer
Shen, Z., & Li, M. (2026) · International Conference on Advanced Algorithms and Neural Networks (AANN) · doi:10.1109/aann71145.2026.11709114
“…on pointwise reconstruction error, Anomaly Transformer characterizes anomalous time points through discrepancies between prior and series associations [10] , while DCdetector enhances discrimination between normal and anomalous patterns through dual-attention contrastive representations [12] .”
SISAD: Semantic Interference Suppression for Multimodal Time-Series Anomaly Detection
Li, S.-R., Deng, P., Liu, J., Wang, Z., Shuang-shuang, P. A. N. G., & Rui-Peng, S. U. N. (2026) · AI · doi:10.3390/ai7100404
“The first is to align event semantics with temporal changes so that event-driven fluctuations can be evaluated using the available contextual evidence [3–6, 9, 11 ].”
GCAT: a graph-convolutional adversarial transformer for multivariate time series anomaly detection
Sefati, S. T., Razavi, S. N., & Salehpoor, P. (2026) · Cluster Computing · doi:10.1007/s10586-026-06635-3
CGAT-PAD: A Consistency-Guided Anomaly Transformer for Photovoltaic Anomaly Detection
Pan, Z., Di, L., & Zhuang, W. (2026) · Sustainable Energy Technologies and Assessments · doi:10.1016/j.seta.2026.105453
COHERE: Collaborative Hypergraph Prototype Learning for Multivariate Time Series Anomaly Detection
Li, M., Zhu, Y., & Sun, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-5696-9_38
Aharon, U., Dubin, R., Dvir, A. Z., & Hajaj, C. (2026) · Computers & Security · doi:10.1016/j.cose.2026.105198
Physical information embedded dual residual network for UAV actuators fault diagnosis
Xue, F., Tan, L., Jin, G., Zhang, C., Wang, H., Gao, J., & Lv, N. (2026) · International Journal of Micro Air Vehicles · doi:10.48130/mav-0026-0018
Self-citationPopereshnyak, S. (2026) · PROBLEMS IN PROGRAMMING · doi:10.15407/pp2026.03.069
Dynamic Sparse Graph Attention for Multivariate Time-Series Anomaly Detection and Localization
Jia, H., Wang, Z., Tang, J., & Yin, S. (2026) · International Conference on Control, Robotics and Intelligent System (CCRIS) · doi:10.1109/ccris71163.2026.11721664
“Recent contrastive attention detectors such as DCdetector also learn discriminative time-series representations without relying only on reconstruction loss [9].”
A Framework for Time-Series Anomaly Detection with Mamba Backbone
Khang, L. H., Vo, C. T. N., & Pham, T. B. N. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-6510-7_14
D-GDA: Dopamine-Gated Differential Attention for Time-Series Anomaly Detection
Nguyen, D. H., Mai, L., & Nguyen, H. H. T. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-5641-9_11
Pérez-Pérez, E.-J. (2026) · Eng—Advances in Engineering · doi:10.3390/eng7100564
Zhang, A., Zhang, H., & Zhang, T. (2026) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-026-03333-9
DRIFT: A Dual-Branch Time-Frequency Transformer for Time Series Anomaly Detection
Wu, J., Xu, J., & Duan, L. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729029
“Results are compared with methods including LSTM-NDT [11], DAGMM [25], MSCRED [19], CAE-M [26], MERLIN [27], MTAD-GAT [10], GDN [12], Anomaly Transformer [28] (AnoTran for short), DCdetector [17], MtsCID [21], and DConAD [18].”
FSA-AD: Frequency-Semantic Anomaly Detection with Adaptive Patching and Orthogonal Prototypes
Liu, L., Qian, Y., Qi, Q., Long, J., & Luo, Y. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729090
Shang, S. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729715
“While existing Transformer-based models, such as Anomaly Transformer[17], DCDetector[19], TranAD[28], and DconAD[29], focus on capturing complex spatio-temporal dependencies, they often overlook the deterministic information in high-frequency residuals, resulting in high-frequency Authorized licensed use limited to th…”
Ma, Y., Yu, J., Li, S., & Hu, Y. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729857
Zhang, Z., & Guo, G. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729856
C2FAD: A Coarse-to-Fine Anomaly Detection for Time Series
Xia, W., Wang, C., Su, S., & Zheng, H. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728694
“Models that focus on global modeling[7, 9] frequently overlook subtle local anomalies, while those that emphasise local details[10, 11] can be misled by normal fluctuations, resulting in an increased number of false alarms.”
Xu, M., Zhang, L., Mao, B., Xu, W., Zheng, X., & Shen, F. (2026) · Big Data and Cognitive Computing · doi:10.3390/bdcc10100359
Liu, W., Liu, M., Xia, F., Qiuyuan, Z., Wei, S., & Yang, W. (2026) · Journal of Engineering and Applied Science · doi:10.1186/s44147-026-01290-2
Calibration-Aware Zero-Shot Time-Series Anomaly Detection with Time-Series Foundation Models
Abbas, S. M., Bangash, Y. A., Du, J., Murtaza, G., & Easwaramoorthy, S. V. (2026) · doi:10.1109/icsl-dsga70378.2026.11736385
“Graph and memory-augmented transformers such as GDN [31], MEMTO [32], the Anomaly Transformer, TranAD, and DCdetector push multivariate accuracy further [17]–[19].”
TFCdetector: Multivariable time series anomaly detection with time-frequency constraints
Fan, J., Zhao, J., Ma, J., & Cai, Y. (2026) · PLoS ONE · doi:10.1371/journal.pone.0361145
Unifying global and local anomaly detection for time series
Lu, T., Ma, S., Zhang, Z., Cui, L., & Lin, X. (2026) · Knowledge and Information Systems · doi:10.1007/s10115-026-02917-9
Metadata
- Authors
- Yang, Y., Zhang, C., Zhou, T., Wen, Q., & Sun, L.
- Affiliations
- University of Oxford (GB)
- Alibaba Group (China) (CN)
- Alibaba Group (United States) (US)
- Venue
- Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
- Publisher
- ACM
- Published
- 2023-08-04
- Pages
- 3033-3045
- OpenAlex
- W4385562572
- Cited by
- 387
- References
- 57
- Citations by year
- 2026: 160 · 2025: 161 · 2024: 65 · 2023: 1
- FWCI
- 68.57
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by-nc-sa)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Physical Sciences › Computer Science › Computer Networks and Communications › Software System Performance and Reliability
- Keywords
- time series anomaly detection, contrastive learning, representation learning, dual attention mechanism, multi-scale representation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
