Learning Sparse Latent Graph Representations for Anomaly Detection in Multivariate Time Series
The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
Abstract
Anomaly detection in high-dimensional time series is typically tackled using either reconstruction- or forecasting-based algorithms due to their abilities to learn compressed data representations and model temporal dependencies, respectively. However, most existing methods disregard the relationships between features, information that would be extremely useful when incorporated into a model. In this work, we introduce Fused Sparse Autoencoder and Graph Net (FuSAGNet), which jointly optimizes reconstruction and forecasting while explicitly modeling the relationships within multivariate time series. Our approach combines Sparse Autoencoder and Graph Neural Network, the latter of which predicts future time series behavior from sparse latent representations learned by the former as well as graph structures learned through recurrent feature embedding. Experimenting on three real-world cyber-physical system datasets, we empirically demonstrate that the proposed method enhances the overall anomaly detection performance, outperforming baseline approaches. Moreover, we show that mining sparse latent patterns from high-dimensional time series improves the robustness of the graph-based forecasting model. Lastly, we conduct visual analyses to investigate the interpretability of both recurrent feature embeddings and sparse latent representations.
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
“Furthermore, VGCRN [83] and FuSAGNet [67] combine two frameworks to achieve more robust and accurate results.”
From Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects (2024) · cites this paper as [67]
Citations
Cites
(2008) · Journal of Machine Learning Research · Cited by 33,051
On Information and Sufficiency
Kullback, S., & Leibler, R. A. (1951) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177729694 · Cited by 20,193
Chandola, V., Banerjee, A., & Kumar, V. (2009) · ACM Computing Surveys · doi:10.1145/1541880.1541882 · Cited by 11,687
Bidirectional recurrent neural networks
Schuster, M., & Paliwal, K. K. (1997) · IEEE Transactions on Signal Processing · doi:10.1109/78.650093 · Cited by 10,172 · cited 1×
“Applicable to RNNs, a bidirectional variant comprises an additional module that processes the input in the backward direction [29]; the resulting forward-and backward-processed outputs are then combined to better characterize the input time series, containing richer information.”
MethodRobust Face Recognition via Sparse Representation
Wright, J., Yang, A. Y., Ganesh, A., Sastry, S. S., & Ma, Y. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2008.79 · Cited by 9,388 · cited 1×
“Adequate sparse representation can enhance data interpretability, in addition to model generalizability by revealing the latent structure of the input data [19, 21, 37].”
BackgroundGraph neural networks: A review of methods and applications
Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., & Sun, M. (2020) · AI Open · doi:10.1016/j.aiopen.2021.01.001 · Cited by 6,880
Graph Neural Networks: A Review of Methods and Applications
Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., & Sun, M. (2018) · arXiv · doi:10.48550/arxiv.1812.08434 · Cited by 6,880
Geometric Deep Learning: Going beyond Euclidean data
Bronstein, M. M., Bruna, J., LeCun, Y., Szlam, A., & Vandergheynst, P. (2017) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2693418 · Cited by 3,661 · cited 1×
“While there exist numerous forms of graphical models, the essence of GNNs in geometric deep learning [7] is the message passing (also referred to as diffusion, propagation, or neighborhood aggregation under different guises) function [6].”
BackgroundThe Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions
Hochreiter, S. (1998) · International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems · doi:10.1142/s0218488598000094 · Cited by 2,939 · cited 1×
“Long Short-Term Memory (LSTM) [27] has been proposed to mitigate the vanishing/exploding gradient problem [14] encountered when training RNNs by introducing a memory cell and three activation-regulated gates that selectively remember/forget information on past observations.”
BackgroundDetecting 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 1×
“Smoothing by moving average is applied to reduce the effect of abrupt changes in anomaly scores, which may have been caused by a trivial glitch under normal operating conditions [15].”
Method
Research works printed but not linked: 15
- Charu C Aggarwal. 2015. Outlier analysis. In Data mining. Springer, 237--263.
- Michael M Bronstein, Joan Bruna, Taco Cohen, and Petar Velickovic. 2021. Geometric deep learning: Grids, groups, graphs, geodesics, and gauges. arXiv preprint arXiv:2104.13478 (2021). · arXiv
- Kyunghyun Cho, Bart Van Merriënboer, Dzmitry Bahdanau, and Yoshua Bengio. 2014. On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014). · arXiv
- Matthias Fey and Jan Eric Lenssen. 2019. Fast graph representation learning with PyTorch Geometric. arXiv preprint arXiv:1903.02428 (2019). · arXiv
- Jonathan Goh, Sridhar Adepu, Khurum Nazir Junejo, and Aditya Mathur. 2016. A dataset to support research in the design of secure water treatment systems. In International conference on critical information infrastructures security. Springer, 88--99.
- Ian J Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, DavidWarde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial networks. arXiv preprint arXiv:1406.2661 (2014). · arXiv
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). · arXiv
- Thomas N Kipf and MaxWelling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016). · arXiv
- Honglak Lee, Chaitanya Ekanadham, and Andrew Ng. 2007. Sparse deep belief net model for visual area V2. Advances in neural information processing systems 20 (2007), 873--880.
- Keiron O'Shea and Ryan Nash. 2015. An introduction to convolutional neural networks. arXiv preprint arXiv:1511.08458 (2015). · arXiv
- Bernhard Schölkopf, John C Platt, John Shawe-Taylor, Alex J Smola, and Robert C Williamson. 2001. Estimating the support of a high-dimensional distribution. Neural computation 13, 7 (2001), 1443--1471.
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. arXiv preprint arXiv:1706.03762 (2017). · arXiv
- Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017). · arXiv
- Hang Zhao, Yujing Wang, Juanyong Duan, Congrui Huang, Defu Cao, Yunhai Tong, Bixiong Xu, Jing Bai, Jie Tong, and Qi Zhang. 2020. Multivariate time-series anomaly detection via graph attention network. arXiv preprint arXiv:2009.02040 (2020). · arXiv
- 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
“3) MTAD-GAT [193] ST Self W ✓ Subseq FuSAGNet [78] ST Semi W Subseq 1 A: Approach, 2 MA: Main Architecture, 3 T/S: Temporal/Spatial | Values: [S:Spatial, T:Temporal, ST:Spatio-Temporal], 4 Su/Un: Supervised/Unsupervised | Values: [Su: Supervised, Un: Unsupervised, Semi: Semi-supervised, Self: Self-supervised], 5 Int:…”
Jin, M., Koh, H. Y., Wen, Q., Zambon, D., Alippi, C., Webb, G. I., King, I., & Pan, S. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3443141 · Cited by 567
“Recently, GNNs have shown promise in capturing temporal and spatial dependencies among variables, addressing this gap [36], [56].”
BackgroundMethodResultInfluentialSelf-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects
Zhang, K., Wen, Q., Zhang, C., Cai, R., Jin, M., Liu, Y., Zhang, J. Y., Liang, Y., Pang, G., Song, D., et al. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3387317 · Cited by 295
“Furthermore,VGCRN[83]andFuSAGNet[67]combine twoframeworkstoachievemorerobustandaccuratere-sults.”
BackgroundQiu, S., Cui, X., Ping, Z., Shan, N., Li, Z., Bao, X., & Xu, X. (2023) · Sensors · doi:10.3390/s23031305 · Cited by 221
“Tennessee Eastman process [155] 2022 Sparse AE and GNN are combined to effectively capture inter-dependencies in high-dimensional sensor data with few anomalies. cyber-physicalsystems”
BackgroundDeep Learning Advancements in Anomaly Detection: A Comprehensive Survey
Huang, H., Wang, P., Pei, J., Wang, J., Alexanian, S., & Niyato, D. T. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3585884 · Cited by 170
“In contrast, Han and Woo [51] take a different approach by introducing sparse AEs to learn sparse latent representations from high-dimensional input data.”
Metadata
- Authors
- Han, S., & Woo, S. S.
- Affiliations
- RTM, Seoul, South Korea
- Sungkyunkwan University (KR)
- Venue
- Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
- Publisher
- ACM
- Published
- 2022-08-14
- Pages
- 2977-2986
- OpenAlex
- W4290943650
- Cited by
- 137
- References
- 20
- Citations by year
- 2026: 28 · 2025: 46 · 2024: 41 · 2023: 22
- FWCI
- 15.07
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion)
- Funders
- IITP by Korean MSIT (Artificial Intelligence Innovation Hub) (2021-0-02068)
- Basic Science Research Program through NRF by Korean MSIT (2020R1C1C1006004)
- IITP by Korean MSIT (Graduate School of Convergence Security at Sungkyunkwan University) (2022-0-01199)
- IITP by Korean MSIT (Self-directed Multi-Modal Intelligence for solving unknown, open domain problems) (2022-0-01045)
- IITP by Korean MSIT (AI Platform to Fully Adapt and Reflect Privacy-Policy Changes) (2022-0-00688)
- IITP by Korean MSIT (AI Graduate School Support Program at Sungkyunkwan University) (2019-0-00421)
- 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 › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
- Keywords
- anomaly detection, multivariate time series, sparse autoencoders, graph neural networks, time series forecasting, feature relationships, cyber-physical systems, interpretability, high-dimensional time series
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Learning Sparse Latent Graph Representations for Anomaly Detection in Multivariate Time Series. https://app.cochat.ai/papers/10.1145/3534678.3539117
- The paper
- Han, S., & Woo, S. S. (2022). Learning Sparse Latent Graph Representations for Anomaly Detection in Multivariate Time Series. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. https://doi.org/10.1145/3534678.3539117
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.