A Semi-Supervised VAE Based Active Anomaly Detection Framework in Multivariate Time Series for Online Systems
The DOI matches its Crossref record; 34 of the 35 references it cites were found in a registry or an index, and 1 are not checked yet.
Abstract
Nowadays, the large online systems are constructed on the basis of microservice architecture. A failure in this architecture may cause a series of failures due to the fault propagation. Thus, the large online systems need to be monitored comprehensively to ensure the service quality. Even though many anomaly detection techniques have been proposed, few of them can be directly applied to a given microservice or cloud server in industrial environment. To settle these challenges, this paper presents SLA-VAE, a semi-supervised learning based active anomaly detection framework using variational auto-encoder. SLA-VAE first defines anomalies based on feature extraction module, introduces semi-supervised VAE to identify anomalies in multivariate time series, and employs active learning to update the online model via a small number of uncertain samples. We conduct experiments on the cloud server data from two different types of game business in Tencent. The results show that SLA-VAE significantly outperforms other state-of-the-art methods and is suitable for wide deployment in large online business system.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Semi-supervised learning approaches aim to train models that generalize across servers and container instances without requiring per-instance training [105]”
From Anomaly detection and root-cause identification in microservices: a survey (2026) · cites this paper as [105]
Citations
Cites
Li, Z., & Hoiem, D. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2773081 · Cited by 4,202
Saliency Detection: A Spectral Residual Approach
Hou, X., & Zhang, L. (2007) · 2007 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2007.383267 · Cited by 3,422 · cited 2×
“In this paper, we adopt the Spectral Residual (SR) algorithm[12] to measure residual errors.”
MethodMicroservices: Yesterday, Today, and Tomorrow
Dragoni, N., Giallorenzo, S., Lafuente, A. L., Mazzara, M., Montesi, F., Mustafin, R., & Safina, L. (2017) · Springer eBooks · doi:10.1007/978-3-319-67425-4_12 · Cited by 2,058
DeepLog: Anomaly Detection and Diagnosis from System Logs through Deep Learning
Du, M., Li, F., Zheng, G., & Srikumar, V. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134015 · Cited by 1,835
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 · cited 5×
“When detecting anomalies in multivariate time series, the existing approaches[7, 13, 17, 20, 21, 25, 30, 33, 37, 39, 40] directly adopt a sequence of observations x t − w : t to calculate the anomaly result of x t at time t .”
BackgroundMethodInfluentialDetecting 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 · cited 5×
“When detecting anomalies in multivariate time series, the existing approaches[7, 13, 17, 20, 21, 25, 30, 33, 37, 39, 40] directly adopt a sequence of observations x t − w : t to calculate the anomaly result of x t at time t .”
BackgroundMethodInfluentialActive Learning with Statistical Models
Cohn, D. A., Ghahramani, Z., & Jordan, M. I. (1996) · Journal of Artificial Intelligence Research · doi:10.1613/jair.295 · Cited by 1,317 · cited 1×
“Second, to optimize the online detection model continuously, we adopt the active learning, which is aimed to learn and update models from small amount of data[5], and propose an active anomaly detection”
MethodTime Series FeatuRe Extraction on basis of Scalable Hypothesis tests (tsfresh – A Python package)
Christ, M., Braun, N., Neuffer, J., & Kempa-Liehr, A. W. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.03.067 · Cited by 1,257 · cited 1×
“Traditional time series feature extraction methods obtain features from statistical, temporal and spectral domains[3, 4, 26, 28].”
MethodMAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks
Li, D., Chen, D., Jin, B., Shi, L., Goh, J., & Ng, S.-K. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-30490-4_56 · Cited by 1,185
A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-Based Variational Autoencoder
Park, D., Hoshi, Y., & Kemp, C. C. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2801475 · Cited by 1,115
Research works printed but not linked: 6
- 10.5555/1622737.1622744 · doi:10.5555/1622737.1622744
- Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114(2013). · arXiv
- Pankaj Malhotra, Lovekesh Vig, Gautam Shroff, and Puneet Agarwal. 2015. Long short term memory networks for anomaly detection in time series. In Proceedings, Vol. 89. 89–94.
- Xuming Ran Mingkun Xu Lingrui Mei Qi Xu and Quanying Liu. 2020. Detecting out-of-distribution samples via variational auto-encoder with reliable uncertainty estimation. arXiv preprint arXiv:2007.08128(2020). · arXiv
- Svante Wold, Kim Esbensen, and Paul Geladi. 1987. Principal component analysis. Chemometrics and intelligent laboratory systems 2, 1-3 (1987), 37–52.
- 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
Deep Learning for Time Series Anomaly Detection: A Survey
Zamanzadeh Darban, Z., Webb, G. I., Pan, S., Aggarwal, C., & Salehi, M. (2025) · ACM Computing Surveys · doi:10.1145/3691338 · Cited by 613
“In order to prevent big losses from total machine failure or even natural disasters, it is necessary to detect OOS anomalies early enough.”
Xin, R., Chen, P., & Zhao, Z. (2023) · Journal of Systems and Software · doi:10.1016/j.jss.2023.111724 · Cited by 99
Self-citationRevisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspective
Wang, Z., Pei, C., Ma, M., Wang, X., Li, Z., Pei, D., Rajmohan, S., Zhang, D., Lin, Q., Zhang, H., et al. (2024) · International World Wide Web Conference (WWW) · doi:10.1145/3589334.3645710 · Cited by 173
Wang, F., Jiang, Y., Zhang, R., Wei, A., Xie, J., & Pang, X. (2025) · Sensors · doi:10.3390/s25010190 · Cited by 119
“SLA-VAE [44] addresses the challenge of obtaining labeled data in InterFusion through semi-supervised learning, utilizing active learning to leverage a small number of highly uncertain samples for learning and updating online system anomaly detection models.”
Zheng, M., Man, J., Wang, D., Chen, Y., Li, Q., & Liu, Y. (2023) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2023.109235 · Cited by 94
Navigating the metric maze: a taxonomy of evaluation metrics for anomaly detection in time series
Sørbø, S., & Ruocco, M. (2024) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-023-00988-8 · Cited by 58
“Here one true positive is recorded for each true anomalous segment with at least one predicted anomalous point, one false negative for each of the rest of the true anomalous segments, and one false positive for any predicted anomalous segment without any true anomalous points.”
RoSAS: Deep semi-supervised anomaly detection with contamination-resilient continuous supervision
Xu, H., Wang, Y., Pang, G., Jian, S., Liu, N., & Wang, Y. (2023) · Information Processing & Management · doi:10.1016/j.ipm.2023.103459 · Cited by 59
“It is also noteworthy that, except for tabular data or images, related studies also consider this semi-supervised learning paradigm of anomaly detection in graph data (Ding et al., 2021; Dou et al., 2020; Zhou et al., 2022) and time series (Carmona et al., 2022; Huang et al., 2022).”
BackgroundA Survey of Time Series Anomaly Detection Methods in the AIOps DomainPreprint
Zhong, Z., Fan, Q., Zhang, J., Ma, M., Zhang, S., Sun, Y., Lin, Q., Zhang, Y., & Pei, D. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.00393 · Cited by 59
“SLA-VAE enables model sharing among entities of the same type, thereby reducing training time.”
MethodInterpretable Failure Localization for Microservice Systems Based on Graph Autoencoder
Sun, Y., Lin, Z., Shi, B., Zhang, S., Ma, S., Jin, P., Zhong, Z., Pan, L., Guo, Y., & Pei, D. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3695999 · Cited by 62
Coupled Attention Networks for Multivariate Time Series Anomaly Detection
Xia, F., Chen, X., Yu, S., Hou, M., Liu, M., & You, L. (2023) · IEEE Transactions on Emerging Topics in Computing · doi:10.1109/tetc.2023.3280577 · Cited by 40
“Many researchers have started using multivariate time series data as input to improve anomaly detection accuracy [9], [11], [12], [19].”
BackgroundTrustworthy AI-based Performance Diagnosis Systems for Cloud Applications: A Review
Xin, R., Wang, J., Chen, P., & Zhao, Z. (2025) · ACM Computing Surveys · doi:10.1145/3701740 · Cited by 30
“Huang et al. [85] present SLA-VAE, a semi-supervised learning anomaly detection framework using VAE.”
Self-citationOpen Anomalous Trajectory Recognition via Probabilistic Metric Learning
Gao, Q., Wang, X., Liu, C., Trajcevski, G., Huang, L., & Zhou, F. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/233 · Cited by 31
“Due to the inherent uncertainty and diversity of trajectories, recent studies use deep generative models to capture the latent variability from complex and varying trajectories [Li et al. , 2018; Liu et al. , 2020; Han et al. , 2022; Huang et al. , 2022].”
BackgroundPAFormer: Anomaly Detection of Time Series With Parallel-Attention Transformer
Bai, N., Wang, X., Han, R., Wang, Q., & Liu, Z. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3337876 · Cited by 25
“With the widespread application of artificial intelligence technology, scholars have applied deep learning to time-series anomaly detection [17], [18], [19], [20], [21], [22], [23], [24], [25].”
WAKE: A Weakly Supervised Business Process Anomaly Detection Framework via a Pre-Trained Autoencoder
Guan, W., Cao, J., Zhao, H., Gu, Y., & Qian, S. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3322411 · Cited by 24
“Ap-proximatelabelscanalsobegeneratedtodetectanomaliesby directlyaddressingtheinsufficiencyoflabels[23],[24],[25].”
MethodRuntime Performance Anomaly Diagnosis in Production HPC Systems Using Active Learning
Aksar, B., Sencan, E., Schwaller, B., Aaziz, O., Leung, V. J., Brandt, J. M., Kulis, B., Egele, M., & Coskun, A. K. (2024) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2024.3365462 · Cited by 21
“Huang et al. [20] and Wang et al. [21] employ unsupervised anomaly detection methods combined with active learning to classify time series windows as either healthy or anomalous.”
BackgroundFedTADBench: Federated Time-series Anomaly Detection Benchmark
Liu, F., Zeng, C. H., Zhang, L., Zhou, Y., Mu, Q., Zhang, Y., Zhang, L., & Zhu, C. (2022) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc-dss-smartcity-dependsys57074.2022.00071 · Cited by 20
“In this study, we focus on detecting anomalies at entitylevel [37] using multivariate time series.”
MethodMonitoring Data for Anomaly Detection in Cloud-Based Systems: A Systematic Mapping Study
Hrusto, A., bin Ali, N., Engström, E., & Wang, Y. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3744556 · Cited by 19
“The classification of monitoring data into metrics, logs, and traces is presented in Tables 6 and 7, together with references to the papers that used these data types for anomaly detection.”
Source-Free Domain Adaptation Framework for Rotary Machine Fault Diagnosis
Jeong, H. Y., Kim, S. J., Seo, D. H., & Kwon, J.-W. (2025) · Sensors · doi:10.3390/s25144383 · Cited by 19
Başaran, O. T., & Dressler, F. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111145 · Cited by 22
“3) SLA-VAE [43]: Model defines anomalies based on their feature extraction module, then introduces semi-supervised VAE to identify anomalies in multivariate time series.”
EST transformer: enhanced spatiotemporal representation learning for time series anomaly detection
Gao, Y., Su, R., Ben, X., & Chen, L. (2025) · Journal of Intelligent Information Systems · doi:10.1007/s10844-025-00918-8 · Cited by 14
“For server machines monitoring, the SLA-VAE (Huang et al., 2022) utilizes a semi-supervised Variational Autoencoder (VAE) to identify anomalies in multivariate time series, which improves the robustness of system.”
A Transferable Time Series Forecasting Service Using Deep Transformer Model for Online Systems
Huang, T., Chen, P., Zhang, J., Li, R., & Wang, R. (2022) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3551349.3560414 · Cited by 14
“Previous works assume that the observations are generated from prior distribution [13, 27].”
BackgroundSelf-citationActive Lifelong Anomaly Detection with Experience Replay
Faber, K., Corizzo, R., Śnieżyński, B., & Japkowicz, N. (2022) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa54385.2022.10032405 · Cited by 20
“A semi-supervised VAE-based approach is proposed in [30], where active learning is used to select a small number of samples leveraging model uncertainty via the evidence of (variational) lower bound (ELBO).”
BackgroundAMAD: Active learning-based multivariate time series anomaly detection for large-scale IT systems
Yu, R., Wang, Y., & Wang, W. (2023) · Computers & Security · doi:10.1016/j.cose.2023.103603 · Cited by 16
The performance of encoder–decoder neural networks for leak detection in water distribution networks
Doss, P. M., Rokstad, M. M., & Tscheikner-Gratl, F. (2024) · Water Science & Technology Water Supply · doi:10.2166/ws.2024.174 · Cited by 13
Identifying Performance Issues in Cloud Service Systems Based on Relational-Temporal Features
Gu, W., Liu, J., Chen, Z., Zhang, J., Su, Y., Gu, J., Feng, C. Q., Yang, Z., Yang, Y., & Lyu, M. R.-T. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3702978 · Cited by 16
Space Decoupled Prototype Learning for Few-Shot Attack Detection in Cyber–Physical Systems
Sun, H., Huang, Y., Zhou, C., Han, L., Liu, H., Chen, J., & Li, X. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3423327 · Cited by 11
“Huang et al. [16] developed a semisupervised learning-based framework named a semi-supervised learning based active anomaly detection framework using variational auto-encoder (SLA-VAE) to detect anomalies in an industrial environment using a variational autoencoder.”
MethodUnited We Stand: Towards End-to-End Log-based Fault Diagnosis via Interactive Multi-Task Learning
He, M., Duan, C., Xiao, P., Jia, T., Yu, S., Zhang, L., Hong, W., Han, J., Wu, Y., Li, Y., et al. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00061 · Cited by 11
“Faults can propagate across servers, causing anomalies within the system and ultimately leading to failures of the entire system [9]–[13].”
Leveraging Large Language Models for Auto-remediation in Microservices Architecture
Sarda, K. (2023) · IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C) · doi:10.1109/acsos-c58168.2023.00025 · Cited by 17
“Current research has focused on automated anomaly detection in microservice architectures [6, 14, 25], but achieving the Autonomous Stage in AIOps requires further progress in RCA and AR. Large Language Models (LLMs) like CodeBert [5], Codex [3], GPT-Neo, and GPT-NeoX [23] show promise for code…”
MethodTime-Series Multi-Instance Learning for Weakly Supervised Industrial Fault Detection
Liu, C., He, S., Li, S., Shi, Z., & Meng, W. (2025) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3523591 · Cited by 8
“Huang et al. [12] proposed a supervised encoder–decoder-based detection system trained with pointwise labels provided by experts.”
Revisiting Backdoor Attacks on Time Series Classification in the Frequency Domain
Huang, Y., Zhang, M., Wang, Z., Li, W., & Yang, M. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714827 · Cited by 12
“The integration of time series classification (TSC) models into web technologies not only supports real-time analytics but also enables predictive capabilities that are vital for adapting to dynamic user needs and market trends [14, 24, 40, 43, 51].”
Generative Models for Time Series Anomaly Detection: A Survey
Cao, J., Miao, J., Tao, H., Wang, Y., Wu, J. X., Wang, Z., & Wu, X. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3614213 · Cited by 12
“Methods demonstrating good performance on these datasets include OmniAnomaly [122], TopoMAD [61], InterFu-sion [89], and SLA-VAE [67].”
InfluentialSun, Y., Liang, M., Zhang, S., Che, Z., Luo, Z., Li, D., Zhang, Y., Pei, D., Pan, L., & Hou, L. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3702984 · Cited by 8
“However, for OmniTransfer , the performance becomes stable after using less than 2 days of training data, while for one model/entity, the performance of most models is unsatisfactory with less than 3 days of training data.”
Sec-Llama: a Compact Fine-Tuned LLM for Network Intrusion Detection in Kubernetes Clusters
Abdennebi, A., Kara, N., Lahlou, L., Younis, M., & Ould‐Slimane, H. (2025) · IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN) · doi:10.1109/icmlcn64995.2025.11140090 · Cited by 6
“[13] employed a semi-supervised learning-based active anomaly detection framework using variational auto-encoder (SLA-VAE).”
Sun, X., Zhu, J., Tang, B., & Jiang, Z. (2025) · Sensors · doi:10.3390/s25113473 · Cited by 5
“The other type uses encoder-decoder architectures to reconstruct observed values and calculate reconstruction errors, with common models including autoencoder neural network (AE) and Variational Autoencoders (VAE) [21–24].”
Towards efficient multi-granular anomaly detection in distributed systems
Tu, C., Chen, M., Zhang, L., Zhao, L., Wu, D., & Yue, Z. (2023) · Array · doi:10.1016/j.array.2023.100330 · Cited by 5
Tang, L., Zhao, Y., Xue, C., Jiang, Z., Zou, W., Liang, Y., & Chen, Q. (2024) · Digital Communications and Networks · doi:10.1016/j.dcan.2024.08.009 · Cited by 6
Anomaly detection and root-cause identification in microservices: a survey
Barata, L. M., Sequeira, S., Lopes, E., Inácio, P. R. M., & Freire, M. M. (2026) · Cluster Computing · doi:10.1007/s10586-026-06095-9 · Cited by 4
“Other semi-supervised contributions include GRU Autoencoders retrained online for adaptability [20], VAEs applied to multi-modal data [105], and frameworks such as AutoLog [60] that exploit normative logs to train baseline autoencoders.”
InfluentialTang, L., Kou, E., Zhang, W., Wu, Q., & Chen, Q. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3448429 · Cited by 4
“In this experiment, BeatGAN [11], SLA-VAE [22], MTAD-GAT [23], MAD-GAN [24], and LSTM-VAE [25] were selected as comparison models.”
E-Commerce Data Anomaly Detection Method Based on Variational Autoencoder
Li, J., Liu, S., & Zou, J. (2024) · International Conference on Artificial Intelligence, Internet of Things and Cloud Computing Technology (AIoTC) · doi:10.1109/aiotc63215.2024.10748279 · Cited by 4
Diagnosing and Resolving Cloud Platform Instability with Multi-modal RAG LLMs
Wang, Y., & Birman, K. (2025) · Workshop on Machine Learning and Systems (EuroMLSys) · doi:10.1145/3721146.3721958 · Cited by 5
Li, X., Jing, J., Wu, T., Zhang, X., & Liu, W. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-025-02757-4 · Cited by 4
“1a, deep learning methods (Lecun et al., 1998; Bank et al., 2023; Goodfellow et al., 2020; Bai & Jing, 2024; Park & Kim, 2025; Huang et al., 2022; Ronneberger et al., 2015) have been proposed to enhance the automation level of anomaly detection.”
A problem-oriented taxonomy of evaluation metrics for time series anomaly detection
Yang, K., Liu, J., Song, Y., Yang, S., & Zhou, Y. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134547 · Cited by 3
Ning, Z., Miao, H., Jiang, Z., & Wang, L. (2024) · Tsinghua Science & Technology · doi:10.26599/tst.2023.9010095 · Cited by 3
Deep Reinforced Active Learning for Time Series Anomaly Detection
Li, H., Xu, H., & Peng, W. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-4752-2_10 · Cited by 3
An Attention Mechanism Based Approach for Multivariate Time Series Anomaly Detection
Xiong, Y., Wang, J., Xin, Y., Zhang, C., & Xue, P. (2023) · International Conference on Dependable Systems and Their Applications (DSA) · doi:10.1109/dsa59317.2023.00030 · Cited by 3
“SLA-VAE [14] introduces a semi-supervised VAE to identify anomalies in multivariate time series and uses active learning to update the online model with a small number of uncertain samples.”
BackgroundA weakly supervised time series anomaly detection method with dual-association discrepancy
Liu, F., Zhang, L., Li, H., Zhou, S., & Zhou, Y. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-024-03119-y · Cited by 3
“• SLA-VAE [19]: a method that involves anomaly labels to construct semi-supervised variational autoencoders for time series anomaly detection.”
Detecting Both Seen and Unseen Anomalies in Time Series
Liu, C., He, S., Li, S., Shi, Z., & Meng, W. (2025) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3717071 · Cited by 5
“First, they are susceptible to irregular signals and overlook regular anomalies [21], resulting in false positives and negatives.”
Yang, J., Wang, Z., Chen, S., He, H., Hou, Y., & Jiang, X. (2025) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2025.3603218 · Cited by 7
“(cid:2) SLA-VAE [11] combines statistical learning based feature extraction and semi-supervised VAE to detect anomalous metrics of servers.”
MAET: A Generalizable Masked Autoencoding Framework for Anomaly Detection in Time-Series Data
Wang, Q., Zhu, H., Zhang, W., Jiang, F., Wang, X., & Huang, H. (2025) · Journal of Signal Processing Systems · doi:10.1007/s11265-025-01968-5 · Cited by 2
“Generative models like Autoencoder (AE) [46, 47], Variational Autoencoder (VAE) [7, 43], Generative Adversarial Network (GAN) [11, 14, 15, 34], and predictive models such as Long Short-Term Memory (LSTM) [41], Recurrent Neural Network (RNN) [ 35], etc., have gradually become mainstream in anomaly…”
Dependable Microservices in the Kubernetes era: A Practitioners Survey
Souza, V. J. S., Neves, V. D. O., & Kimura, B. Y. L. (2024) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · doi:10.5753/jisa.2024.4000 · Cited by 5
He, Z., Chen, P., & Zheng, Z. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3712195 · Cited by 2
“Some recent work [22] also propose to fine-tune an anomaly detection model through active learning or re-training.”
InfluentialSelf-citationWeakly-supervised anomaly detection based on adversarial transfer learning
Chi, J., & Mao, Z. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110975 · Cited by 3
Variational auto encoder fused with Gaussian process for unsupervised anomaly detection
Guan, Y., Xu, Y., Xi, Y., & Li, D. (2023) · The Journal of Supercomputing · doi:10.1007/s11227-023-05747-6 · Cited by 1
Dual Temporal Masked Modeling for KPI Anomaly Detection via Similarity Aggregation
Yu, T., Gao, Z., Xu, K., Wang, X., Shi, P., Ding, B., & Feng, D. (2024) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2024.3486167 · Cited by 1
“Hence, some methods attempt to incorporate certain supervised information, as demonstrated by Huang et al. [13], who combine active learning and variational autoencoders to boost accuracy.”
Anomaly Detection for Coal-fired Boiler via Adversarial VAE Based Method
Zhu, G., Zhou, H., Wang, X., & Wang, Q. (2024) · International Conference on Mobility, Sensing and Networking (MSN) · doi:10.1109/msn63567.2024.00148 · Cited by 1
Bayesian-Adaptive Graph Neural Network for Anomaly Detection (BAGNN)
Ding, Y. S., Zhang, C., Tang, S., Yang, C., & Liang, H. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3543-9_26 · Cited by 1
Liu, H., Huang, X., Jia, M., Jia, T., Wu, Z., Li, Y., Wang, Y., Tan, Y., Zhu, L., & Zhou, W. (2026) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2026.3684516 · Cited by 1
“O NLINE service systems, which support large-scale applications such as social networking [3], [4], search [5], [6], e-commerce [7], [8], and finance [9], [10], [11], operate under high concurrency, dynamic workloads, and distributed execution environments.”
Learning to discover anomalous spatiotemporal trajectory via Open-world State Space model
Gao, Q., Liu, C., Huang, L., Trajcevski, G., Guo, Q., & Zhou, F. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112918 · Cited by 1
AnoF-Diff: One-Step Diffusion-Based Anomaly Detection for Forceful Tool UsePreprint
Lin, Y., Huang, Z., Yang, F., & Berenson, D. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.15153 · Cited by 2
“Examples of reconstruction-based methods include Convolutional and LSTM-based autoen-coders (AE) [29][30], LSTM-based variational autoencoders (VAEs)[31][32][33], and transformer-based reconstruction models, Anomaly Transformer[34].”
Learning models on healthcare data with quality indicators
Tiano, D. (2022) · theses.fr (ABES) · doi:10.70675/0f486610z4301z459bz94a9z257cb65f7bc9
DashChef: A Metric Recommendation Service for Online Systems Using Graph Learning
He, Z., Huang, T., Chen, P., Li, R., Wang, R., & Zheng, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-66456-4_1
Self-citationDQS: a low-budget query strategy for enhancing unsupervised data-driven anomaly detection approaches
Correia, L., Goos, J.-C., Bäck, T., & Kononova, A. V. (2026) · Journal Of Big Data · doi:10.1186/s40537-026-01524-3
“…query strategy at an arbitrary round q Require: Candidate Score Set C as , Query Score Set Q as 1: The second, named the top-based query strategy (TQS) [32, 37, 2, 35, 15, 39], represents a scenario where the B samples with the highest anomaly score are queried, as shown in Algorithm 3.”
MGG-AD: Multi-Granularity Graph-Based Anomaly Detection in IoT Systems
Li, Y., Zhou, Z., Sedlak, B., & Dustdar, S. (2025) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws67624.2025.00096
“To detect abnormal behavior in such IoT systems, the monitoring process can be split into multiple web services that are executed on geographically distributed edge devices [4].”
RFformer: Rectified Flow Transformer for Time Series Anomaly Detection
Hui, D., Zhu, H., Liu, S., Yang, M., Yi, C., & Wei, B. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-4987-0_14
Traffic Anomaly Detection via Dimension-Aware Multi-View Alignment
Yu, H., He, Y., Guo, Y., Li, Z., Geng, K., Zhu, C., & Fang, L. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463205
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
“Reconstruction-based methods [6], such as Autoencoder, VAE, and OmniAnomaly, detect anomalies through reconstruction errors, but they may overfit normal perturbations under stochastic industrial fluc-tuations.”
Wu, S., Zhang, W., Wang, F., Wang, C., Cui, X., Zh, J., & Ma, J. (2026) · International Conference on Electrical Technology and Automatic Control (ICETAC) · doi:10.1109/icetac70565.2026.11636091
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
“Semi-supervised variants, such as SLA-VAE [54], exploit a small set of labelled anomalies to sharpen the separation between normal and abnormal behaviors.”
Active graph anomaly detection
Agarwal, I. (2024) · Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)
Jia, X., Wang, S., Yang, K., Du, L., & Hu, Z. (2026) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3799682.3840774
Metadata
- Authors
- Huang, T., Chen, P., & Li, R.
- Affiliations
- Tencent (China) (CN)
- Sun Yat-sen University (CN)
- Venue
- Proceedings of the ACM Web Conference 2022
- Publisher
- ACM
- Published
- 2022-04-25
- Pages
- 1797-1806
- OpenAlex
- W4224315779
- Cited by
- 61
- References
- 34
- Citations by year
- 2026: 9 · 2025: 19 · 2024: 16 · 2023: 14 · 2022: 3
- FWCI
- 12.60
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International World Wide Web Conference (WWW) (publishedVersion)
- Funders
- Key-Area Research and Development Program of Guangdong Province (No. 2020B010165002)
- Basic and Applied Basic Research of Guangzhou (No. 202002030328)
- National Key Research and Development Program of China (2019YFB1804002)
- National Natural Science Foundation of China (No. 61802448)
- Natural Science Foundation of Guangdong Province (No. 2019A1515012229)
- Tencent Rhino-Bird Joint Research Program (No.K21-67000-059)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Software System Performance and Reliability
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Keywords
- anomaly detection, semi-supervised learning, variational autoencoder, active learning (machine learning), multivariate time series, microservices, fault propagation
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.