A Spatiotemporal Deep Learning Approach for Unsupervised Anomaly Detection in Cloud Systems
The DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.
Abstract
Anomaly detection is a critical task for maintaining the performance of a cloud system. Using data-driven methods to address this issue is the mainstream in recent years. However, due to the lack of labeled data for training in practice, it is necessary to enable an anomaly detection model trained on contaminated data in an unsupervised way. Besides, with the increasing complexity of cloud systems, effectively organizing data collected from a wide range of components of a system and modeling spatiotemporal dependence among them become a challenge. In this article, we propose TopoMAD, a stochastic seq2seq model which can robustly model spatial and temporal dependence among contaminated data. We include system topological information to organize metrics from different components and apply sliding windows over metrics collected continuously to capture the temporal dependence. We extract spatial features with the help of graph neural networks and temporal features with long short-term memory networks. Moreover, we develop our model based on variational auto-encoder, enabling it to work well robustly even when trained on contaminated data. Our approach is validated on the run-time performance data collected from two representative cloud systems, namely, a big data batch processing system and a microservice-based transaction processing system. The experimental results show that TopoMAD outperforms some state-of-the-art methods on these two data sets.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Chandola, V., Banerjee, A., & Kumar, V. (2009) · ACM Computing Surveys · doi:10.1145/1541880.1541882 · Cited by 11,687 · cited 1×
“Traditional approaches [20] include statistical approaches, such as Gaussian-based model, classification-based approaches, such as one-class support vector machines (OC-SVMs) [21], nearest neighbor-based approaches, such as local outlier factor (LOF) [22], and so on.”
MethodEmpirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.3555 · Cited by 11,008
A Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2978386 · Cited by 11,000 · cited 1×
“Many current approaches [48] apply graph neural networks together with RNN and CNN to simultaneously consider spatial and temporal relations.”
MethodPractical Bayesian Optimization of Machine Learning Algorithms
Snoek, J., Larochelle, H., & Adams, R. P. (2012) · arXiv · doi:10.48550/arxiv.1206.2944 · Cited by 6,691
The relationship between Precision-Recall and ROC curves
Davis, J., & Goadrich, M. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143874 · Cited by 6,559
Factor graphs and the sum-product algorithm
Kschischang, F. R., Frey, B. J., & Loeliger, H.-A. (2001) · IEEE Transactions on Information Theory · doi:10.1109/18.910572 · Cited by 6,486 · cited 1×
“Jain et al. [62] parameterize a spatiotemporal graph with a factor graph [63] and then represent each factor with an RNN. Compared with these methods, we directly replace the linear layers in LSTM with state-of-the-art graph neural layers to perform spatiotemporal learning.”
MethodSpatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
Yan, S., Xiong, Y., & Lin, D. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12328 · Cited by 5,410 · cited 1×
“CNN-GCN [51] overcomes this problem through a complete convolutional structure which interleaves 1-D-CNN with GCN. ST-GCN [52] extends a temporal flow as graph edges and then extracts both temporal and spatial features using a unified GCN to perform human action recognition.”
MethodLOF: identifying density-based local outliers
Breunig, M. M., Kriegel, H.-P., Ng, R. T., & Sander, J. (2000) · ACM SIGMOD Record · doi:10.1145/335191.335388 · Cited by 5,207
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 8×
“Some work [11], [12], [47] has provided some practices for threshold selection.”
BackgroundMethodResultInfluentialDetecting 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 3×
“Some work [11], [12], [47] has provided some practices for threshold selection.”
BackgroundMethodScheduled Sampling for Sequence Prediction with Recurrent Neural Networks
Bengio, S., Vinyals, O., Jaitly, N., & Shazeer, N. (2015) · arXiv · doi:10.48550/arxiv.1506.03099 · Cited by 1,621
Deep Learning for Anomaly Detection: A Survey
Chalapathy, R., & Chawla, S. (2019) · arXiv · doi:10.48550/arxiv.1901.03407 · Cited by 1,240 · cited 1×
“Integration of the capacity of modeling dependence in data with complex structure in deep learning-based models and a diversity of assumptions in traditional models is worth of a try, which is denoted as a deep hybrid model in [79].”
BackgroundStructural-RNN: Deep Learning on Spatio-Temporal Graphs
Jain, A., Zamir, A. R., Savarese, S., & Saxena, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.573 · Cited by 1,133 · cited 1×
“Jain et al. [62] parameterize a spatiotemporal graph with a factor graph [63] and then represent each factor with an RNN. Compared with these methods, we directly replace the linear layers in LSTM with state-of-the-art graph neural layers to perform spatiotemporal learning.”
MethodLSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection
Malhotra, P., Ramakrishnan, A., Anand, G., Vig, L., Agarwal, P., & Shroff, G. (2016) · arXiv · doi:10.48550/arxiv.1607.00148 · Cited by 819 · cited 3×
“However, quite a few methods, such as [3] and [9] neglect this phase and only enumerate all thresholds to gain the best F1 score and use it as the performance metric of an anomaly detector.”
MethodRobust log-based anomaly detection on unstable log data
Zhang, X., Xu, Y., Lin, Q., Qiao, B., Zhang, H., Dang, Y., Xie, C., Yang, X., Cheng, Q., Li, Z., et al. (2019) · Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering · doi:10.1145/3338906.3338931 · Cited by 761
LogAnomaly: Unsupervised Detection of Sequential and Quantitative Anomalies in Unstructured Logs
Meng, W., Liu, Y., Zhu, Y., Zhang, S., Pei, D., Liu, Y., Chen, Y., Zhang, R., Tao, S., Sun, P., et al. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/658 · Cited by 708
Time-Series Anomaly Detection Service at Microsoft
Ren, H., Xu, B., Wang, Y., Yi, C., Huang, C., Kou, X., Xing, T., Yang, M., Tong, J., & Zhang, Q. (2019) · Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3292500.3330680 · Cited by 623
Self-citationZhou, X., Peng, X., Xie, T., Sun, J., Ji, C., Li, W., & Ding, D. (2021) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2018.2887384 · Cited by 410 · cited 2×
“For example, Zhou et al. [29] investigate application faults in microservice systems with different root causes and the debugging practice for them.”
BackgroundDeep Structured Energy Based Models for Anomaly Detection
Zhai, S., Cheng, Y., Lu, W., & Zhang, Z. (2016) · arXiv · doi:10.48550/arxiv.1605.07717 · Cited by 334 · cited 3×
“There also exists complex but more powerful temporal modeling techniques, such as time series decomposition [32], spectral residual [6], and some deep learning-based methods [3], [8]–[10] mentioned in Section II-A.”
BackgroundMethodZhou, X., Peng, X., Xie, T., Sun, J., Ji, C., Liu, D., Xiang, Q., & He, C. (2019) · Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering · doi:10.1145/3338906.3338961 · Cited by 277 · cited 1×
“Multiple work [26], [29], [30] has been conducted on the analysis of failure characteristics in cloud systems.”
BackgroundAIOps: Real-World Challenges and Research Innovations
Dang, Y., Lin, Q., & Huang, P. (2019) · 2019 IEEE/ACM 41st International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse-companion.2019.00023 · Cited by 238
MS-Rank: Multi-Metric and Self-Adaptive Root Cause Diagnosis for Microservice Applications
Ma, M., Lin, W., Pan, D., & Wang, P. (2019) · 2019 IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws.2019.00022 · Cited by 58 · cited 1×
“Some work [41] calculates statistical features (such as mean, standard deviation, and gradient) of data in the sliding window as temporal features.”
Background
Research works printed but not linked: 55
- 10.1145/3097983.3098144 · DOI · Paper page
- 10.1145/3178876.3185996 · DOI · Paper page
- 10.1109/PCCC.2018.8710885 · DOI · Paper page
- 10.1109/INFOCOM.2019.8737430 · DOI
- 10.1109/BigData.Congress.2013.60 · DOI · Paper page
- Malhotra, Long short term memory networks for anomaly detection in time series, 89
- 10.1609/aaai.v33i01.33011409 · DOI · Paper page
- An, 2015, Variational autoencoder based anomaly detection using reconstruction probability, Special Lect. IE, 2, 1
- 10.1109/TNNLS.2020.2980749 · DOI · Paper page
- Kingma, Auto-encoding variational Bayes, 1
- Kipf, Semi-supervised classification with graph convolutional networks, 1
- Veličković, Graph attention networks, 1
- 10.1162/089976600300015015 · DOI · Paper page
- Schölkopf, Support vector method for novelty detection, 582
- 10.1007/3-540-46145-0_17 · DOI · Paper page
- 10.1007/978-3-642-35527-1_60 · DOI
- 10.1109/COMPSACW.2013.28 · DOI
- 10.1145/1807128.1807161 · DOI · Paper page
- 10.1109/INFOCOM.2014.6848128 · DOI · Paper page
- 10.1145/3236024.3236060 · DOI · Paper page
- 10.1145/3317550.3321438 · DOI · Paper page
- Vallis, A novel technique for long-term anomaly detection in the cloud, 15
- 10.1109/NOMS.2010.5488443 · DOI · Paper page
- 10.1109/ISSRE.2016.21 · DOI · Paper page
- Khadke, Transparent system call based performance debugging for cloud computing
- 10.1109/TCC.2015.2415813 · doi:10.1109/tcc.2015.2415813
- 10.1145/3297858.3304004 · DOI · Paper page
- 10.1109/DSN.2013.6575304 · DOI
- 10.1109/BigData.2013.6691701 · doi:10.1109/bigdata.2013.6691701
- 10.1145/2939672.2939765 · DOI
- 10.1109/TSC.2011.42 · DOI
- 10.1109/CLUSTER.2018.00039 · DOI
- Li, Diffusion convolutional recurrent neural network: Data-driven traffic forecasting, 1
- 10.24963/ijcai.2018/505 · DOI · Paper page
- Barham, Using magpie for request extraction and workload modelling, 4, 18
- Fonseca, X-trace: A pervasive network tracing framework, 271
- Chen, Automating network application dependency discovery: Experiences, limitations, and new solutions, 8, 117
- 10.1109/IC2E.2014.86 · doi:10.1109/ic2e.2014.86
- 10.1146/annurev.neuro.26.041002.131047 · DOI · Paper page
- Vaswani, Attention is all you need, 5998
- 10.1007/978-3-319-46448-0_8 · DOI · Paper page
- 10.1162/tacl_a_00049 · DOI · Paper page
- 10.1007/978-1-4757-4145-2 · DOI · Paper page
- Sutskever, Sequence to sequence learning with neural networks, 3104
- 10.1109/ICDEW.2010.5452747 · DOI · Paper page
- 2020, HDFS-448
- 2020, HDFS-8160
- 2020, Telegraf
- 2020, Cloudwatch
- 2019, Hipster Shop: Cloud-Native Microservices Demo Application
- 2019, Kubernetes
- Fey, 2019, Fast graph representation learning with PyTorch geometric
- Frazier, 2018, A tutorial on Bayesian optimization
- 10.1145/3292500.3330925 · DOI · Paper page
- 10.1007/978-3-030-03596-9_1 · DOI · Paper page
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
Wang, F., Jiang, Y., Zhang, R., Wei, A., Xie, J., & Pang, X. (2025) · Sensors · doi:10.3390/s25010190 · Cited by 119
Huang, T., Chen, P., & Li, R. (2022) · Proceedings of the ACM Web Conference 2022 · doi:10.1145/3485447.3511984 · Cited by 61
“A great amount of multivariate time series anomaly detection techniques[1, 6, 7, 11, 13, 16, 17, 19–21, 25, 33, 35, 37–40] have been proposed in recent years.”
BackgroundSelf-citationNavigating 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
“14, where the event-based metrics prioritize the cluster of three events over the single long one.”
TraceGra: A trace-based anomaly detection for microservice using graph deep learning
Chen, J., Liu, F., Jiang, J., Zhong, G., Xu, D., Tan, Z., & Shi, S. (2023) · Computer Communications · doi:10.1016/j.comcom.2023.03.028 · Cited by 55
Metadata
- Authors
- He, Z., Chen, P., Li, X., Wang, Y., Yu, G., Chen, C., Li, X., & Zheng, Z.
- Venue
- IEEE Transactions on Neural Networks and Learning Systems
- Published
- 2023-04
- Volume
- 34
- Issue
- 4
- Pages
- 1705-1719
- ISSN
- 2162-237X (ISSN-L)
- 2162-2388
- OpenAlex
- W3093074257
- Cited by
- 148
- References
- 24
- FWCI
- 6.48
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Funders
- National Key Research and Development Program of China (2019YFB1804002)
- Research Development Plan of Key Areas in Guangdong Province (2020B010165002)
- Natural Science Foundation of China (U1811462, 61802448)
- Basic and Applied Basic Research of Guangzhou (202002030328)
- Natural Science Foundation of Guangdong Province (2019A1515012229)
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.