Author(s)

Huiwen Chen ¹, Mingwei Li ¹, Yutian Xu ¹, Hongfei Zhang ¹, Siqi Zhang ¹

Affiliation(s)

¹ School of Science, Northeastern University at Qinhuangdao, Qinhuangdao, China

Corresponding Author

Mingwei Li

ABSTRACT

The increasing number of high-dimensional time series data poses challenges for traditional anomaly detection methods that rely on supervised approaches. In this paper, we propose a stable and novel method called dual adversarial learning graph anomaly detection, which effectively captures complex data relationships and accurately detects anomalies away from them. Our framework utilizes a graph structure to capture complex relationships between variables, while the dual adversarial training overcomes the inherent limitations of autoencoders. In addition, we incorporate the prediction techniques to enhance the ability to identify anomalies. We evaluate our proposed model on publicly available real-world datasets and compare its performance against various existing methods. The experimental results demonstrate that our method achieves more accurate anomaly detection compared to baseline methods.

KEYWORDS

Time Series; Anomaly Detection; Adversarial Training; Prediction; Autoencoder

CITE THIS PAPER

Huiwen Chen, Mingwei Li, Yutian Xu, Hongfei Zhang, Siqi Zhang, DAGAD: Dual Adversarial Learning Graph Anomaly Detection in Multivariate Time Series Data. Journal of Electronics and Information Science (2025) Vol. 10: 114-126. DOI: http://dx.doi.org/10.23977/10.23977/jeis.2025.100116.

REFERENCES

[1] X. Tang, S. Zeng, F. Yu, W. Yu, Z. Sheng, Z.J.N. Kang, Self-supervised anomaly pattern detection for large scale industrial data, Neurocomputing, 515 (2023) 1-12. 
[2] N. Twomey, H. Chen, T. Diethe, P.J.N. Flach, An application of hierarchical Gaussian processes to the detection of anomalies in star light curves, Neurocomputing, 342 (2019) 152-163.
[3] S. Chawla, A. Gionis, k-means–: A unified approach to clustering and outlier detection, Proceedings of the 2013 SIAM international conference on data mining, (SIAM2013), pp. 189-197.
[4] K. Sheridan, T.G. Puranik, E. Mangortey, O.J. Pinon-Fischer, M. Kirby, D.N. Mavris, An application of dbscan clustering for flight anomaly detection during the approach phase, AIAA Scitech 2020 Forum2020), pp. 1851.
[5] Z.K. Maseer, R. Yusof, N. Bahaman, S.A. Mostafa, C.F.M.J.I.a. Foozy, Benchmarking of machine learning for anomaly based intrusion detection systems in the CICIDS2017 dataset, IEEE access, 9 (2021) 22351-22370. https://doi.org/10.1109/ACCESS.2021.3056614
[6] X. Song, M. Wu, C. Jermaine, S.J.I.T.o.k. Ranka, D. Engineering, Conditional anomaly detection, IEEE Transactions on knowledge Data Engineering, 19 (2007) 631-645.
[7] Y. Su, Y. Zhao, C. Niu, R. Liu, W. Sun, D. Pei, Robust anomaly detection for multivariate time series through stochastic recurrent neural network, Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining2019), pp. 2828-2837. https://doi.org/10.1145/3292500.3330672
[8] P. Malhotra, A. Ramakrishnan, G. Anand, L. Vig, P. Agarwal, G.J.a.p.a. Shroff, LSTM-based encoder-decoder for multi-sensor anomaly detection, ICML 2016 Anomaly Detection Workshop, New York, NY, USA, 20162016). https://doi.org/10.48550/arXiv.1607.00148
[9] C. Zhang, D. Song, Y. Chen, X. Feng, C. Lumezanu, W. Cheng, J. Ni, B. Zong, H. Chen, N.V. Chawla, A deep neural network for unsup-evised anomaly detection and diagnosis in multivariate time series data, Proceedings of the AAAI conference on artificial intelligence2019), pp. 1409-1416. https://doi.org/10.48550/arXiv.1811.08055
[10] S. Abilasha, S. Bhadra, P. Deepak, A.J.N. Mathew, Warping resilient scalable anomaly detection in time series, Neurocomputing, 511 (2022) 22-33.
[11] Rumellhart, D. E. "Learning internal representations by error propagation." Parallel distributed processing: explorations in the microstructure of cognition 1 (1986): 319-362.
[12] B. Zong, Q. Song, M.R. Min, W. Cheng, C. Lumezanu, D. Cho, H. Chen, Deep autoencoding gaussian mixture model for unsupervised anomaly detection,  International conference on learning representations2018).
[13] J. Audibert, P. Michiardi, F. Guyard, S. Marti, M.A. Zuluaga, Usad: Unsupervised anomaly detection on multivariate time series,  Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining2020), pp. 3395-3404.
[14] H. Zenati, M. Romain, C.-S. Foo, B. Lecouat, V. Chandrasekhar, Adversarially learned anomaly detection, 2018 IEEE International conference on data mining (ICDM), (IEEE2018), pp. 727-736. https://doi.org/10.1109/ICDM. 2018.00088
[15] H. Zhao, Y. Wang, J. Duan, C. Huang, D. Cao, Y. Tong, B. Xu, J. Bai, J. Tong, Q. Zhang, Multivariate time-series anomaly detection via graph attention network, 2020 IEEE International Conference on Data Mining (ICDM), (IEEE2020), pp. 841-850.
[16] A. Deng, B. Hooi, Graph neural network-based anomaly detection in multivariate time series, Proceedings of the AAAI conference on artificial intelligence2021), pp. 4027-4035.
[17] M.-L. Shyu, S.-C. Chen, K. Sarinnapakorn, L. Chang, A novel anomaly detection scheme based on principal component classifier,  Proce-edings of the IEEE foundations and new directions of data mining workshop, (IEEE Press2003), pp. 172-179.
[18] F.T. Liu, K.M. Ting, Z.-H. Zhou, Isolation forest, 2008 eighth ieee international conference on data mining, (IEEE2008), pp. 413-422. https://doi.org/10.1109/ICDM.2008.17
[19] P. Boniol, J. Paparrizos, T. Palpanas, M.J.J.P.o.t.V.E. Franklin, SAND: streaming subsequence anomaly detection, Proceedings of the VLDB Endowment, 14 (2021) 1717-1729. https://doi.org/10.14778/3467861.3467863
[20] Y. Wang, N. Masoud, A.J.I.t.o.i.t.s. Khojandi, Real-time sensor anomaly detection and recovery in connected automated vehicle sensors, IEEE transactions on intelligent transportation systems, 22 (2020) 1411-1421. https://doi.org/10.1109/TITS.2020.2970295
[21] M. Fahim, K. Fraz, A.J.I.S. Sillitti, TSI: Time series to imaging based model for detecting anomalous energy consumption in smart buildings, Information Sciences, 523 (2020) 1-13.
[22] O. Salem, A. Guerassimov, A. Mehaoua, A. Marcus, B.J.I.J.o.E.-H. Furht, M. Communications, Anomaly detection in medical wireless sensor networks using SVM and linear regression models, International Journal of E-Health Medical Communications, 5 (2014) 20-45. https://doi.org/10.1016/j.procs.2015.10.026
[23] A.H. Yaacob, I.K. Tan, S.F. Chien, H.K. Tan, Arima based network anomaly detection, 2010 Second International Conference on Comm-unication Software and Networks, (IEEE2010), pp. 205-209. https://doi.org/10.1109/ICCSN.2010.55
[24] Z. Niu, K. Yu, X.J.S. Wu, LSTM-based VAE-GAN for time-series anomaly detection, Sensors, 20 (2020) 3738. https://doi.org/10.3390/s20133738
[25] X. Shi, Z. Chen, H. Wang, D.-Y. Yeung, W.-K. Wong, W.-c.J.A.i.n.i.p.s. Woo, Convolutional LSTM network: A machine learning appro-ach for precipitation nowcasting, Advances in neural information processing systems, 28 (2015).
[26] D. Park, Y. Hoshi, C.C.J.I.R. Kemp, A. Letters, A multimodal anomaly detector for robot-assisted feeding using an lstm-based variational autoencoder, IEEE Robotics Automation Letters, 3 (2018) 1544-1551. https://doi.org/10.1109/LRA.2018.2801475
[27] D. Li, D. Chen, B. Jin, L. Shi, J. Goh, S.-K. Ng, MAD-GAN: Multivariate anomaly detection for time series data with generative adversa-rial networks, International conference on artificial neural networks, (Springer2019), pp. 703-716.
[28] M. Defferrard, X. Bresson, P.J.A.i.n.i.p.s. Vandergheynst, Convolutional neural networks on graphs with fast localized spectral filtering, Advances in neural information processing systems, 29 (2016). https://doi.org/10.48550/arXiv.1606.09375
[29] T.N. Kipf, M.J.a.p.a. Welling, Semi-supervised classification with graph convolutional networks, ICLR 20172016). https://doi.org/10.48550/arXiv.1609.02907
[30] Y. Li, H.S. Abdel-Khalik, A. Al Rashdan, J.J.A.o.N.E. Farber, Feature extraction for subtle anomaly detection using semi-supervised learning, Annals of Nuclear Energy, 181 (2023) 109503. https://doi.org/10.1016/j.anucene.2022.109503
[31] A. Siffer, P.-A. Fouque, A. Termier, C. Largouet, Anomaly detection in streams with extreme value theory, Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining2017), pp. 1067-1075.
[32] N. Bezak, M. Brilly, M.J.H.S.J. Šraj, Comparison between the peaks-over-threshold method and the annual maximum method for flood frequency analysis, Hydrological Sciences Journal, 59 (2014) 959-977. https://doi.org/10.1080/02626667.2013.831174
[33] R. Wu, E.J.I.T.o.K. Keogh, D. Engineering, Current time series anomaly detection benchmarks are flawed and are creating the illusion of progress, IEEE Transactions on Knowledge Data Engineering, (2021). https://doi.org/10.48550/arXiv.2009.13807

Sponsors, Associates, and Links

---

• Information Systems and Signal Processing Journal
  
  
• Intelligent Robots and Systems
  
  
• Journal of Image, Video and Signals
  
  
• Transactions on Real-Time and Embedded Systems
  
  
• Journal of Electromagnetic Interference and Compatibility
  
  
• Acoustics, Speech and Signal Processing
  
  
• Journal of Power Electronics, Machines and Drives
  
  
• Journal of Electro Optics and Lasers
  
  
• Journal of Integrated Circuits Design and Test
  
  
• Journal of Ultrasonics
  
  
• Antennas and Propagation
  
  
• Optical Communications
  
  
• Solid-State Circuits and Systems-on-a-Chip
  
  
• Field-Programmable Gate Arrays
  
  
• Vehicular Electronics and Safety
  
  
• Optical Fiber Sensor and Communication
  
  
• Journal of Low Power Electronics and Design
  
  
• Infrared and Millimeter Wave
  
  
• Detection Technology and Automation Equipment
  
  
• Journal of Radio and Wireless
  
  
• Journal of Microwave and Terahertz Engineering
  
  
• Journal of Communication, Control and Computing
  
  
• International Journal of Surveying and Mapping
  
  
• Information Retrieval, Systems and Services
  
  
• Journal of Biometrics, Identity and Security
  
  
• Journal of Avionics, Radar and Sonar