Spatiotemporal Graph Neural Network-Incorporated Latent Factorization of Tensors for Dynamic QoS Estimation

Xin Luo; Fanghui Bi; Tiantian He

doi:10.1109/JAS.2025.125750

Volume 13 Issue 7

Jul. 2026

IEEE/CAA Journal of Automatica Sinica

JCR Impact Factor: 18.3, Top 1 (SCI Q1)

CiteScore: 28.2, Top 1% (Q1)
Google Scholar h5-index: 95， TOP 5

Turn off MathJax

Article Contents

Article Navigation > IEEE/CAA Journal of Automatica Sinica > 2026 > 13(7): 1642-1656

X. Luo, F. Bi, and T. He, “Spatiotemporal graph neural network-incorporated latent factorization of tensors for dynamic QoS estimation,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 7, pp. 1642–1656, Jul. 2026. doi: 10.1109/JAS.2025.125750

Citation:

X. Luo, F. Bi, and T. He, “Spatiotemporal graph neural network-incorporated latent factorization of tensors for dynamic QoS estimation,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 7, pp. 1642–1656, Jul. 2026. doi: 10.1109/JAS.2025.125750

Citation:

PDF( 2190 KB)

Spatiotemporal Graph Neural Network-Incorporated Latent Factorization of Tensors for Dynamic QoS Estimation

doi: 10.1109/JAS.2025.125750

Funds: This work was supported by the National Key Research and Development Program of China (2024YFF0908200), the National Natural Science Foundation of China (62272078), and Chongqing Natural Science Foundation (CSTB2023NSCQ-LZX0069)

More Information

Author Bio:
Xin Luo (Fellow, IEEE) received the B.S. degree in computer science from the University of Electronic Science and Technology of China in 2005, and the Ph.D. degree in computer science from the Beihang University in 2011. He is currently a Distinguished Professor of data science and computational intelligence, and serving as the Dean of the College of Computer and Information Science, and the School of Software, Southwest University. His research interests include data science, graph learning, and tensor network. He has authored or coauthored over 400 papers (including over 200 IEEE Transactions/Journal papers) in the areas of artificial intelligence and data science, receiving 22 000+ Google Scholar citations with the H-Index of 89. He was the recipient of the Outstanding Associate Editor Award from IEEE Access in 2018, IEEE/CAA Journal of Automatica Sinica in 2020, and from IEEE Transactions on Neural Networks and Learning Systems in 2022–2024. He is currently serving as an Associate Editor for IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on System Man and Cybernetics: Systems, IEEE/CAA Journal of Automatica Sinica, Neurocomputing, and Expert Systems with Applications

Fanghui Bi received the B.S. degree in software engineering from the Northeastern University in 2020, and the Ph.D. degree in computer science from the University of Chinese Academy of Sciences in 2025. He is currently a Senior Algorithm Engineer with NetEase. His research interests include big data analytics and graph neural networks

Tiantian He (Member, IEEE) received the Ph.D. degree in computer science from the Hong Kong Polytechnic University, Hong Kong, China, in 2017. Currently, he is a Senior Scientist at Center for Frontier AI Research (CFAR), Institute of High Performance Computing (IHPC), Singapore Institute of Manufacturing Technology (SIMTech), Agency for Science, Technology and Research (A*STAR), Singapore. His research interests include artificial intelligence, machine learning, data-centric transfer optimization, and data mining
Corresponding author: Xin Luo, e-mail: luoxin@ieee.org
Received Date: 2025-01-06
Revised Date: 2025-06-03
Accepted Date: 2025-07-16

Available Online: 2026-07-20

Abstract

Abstract

Quality of service (QoS) data that characterize historical user-service invocations that vary over time are vital to discovering patterns of cloud services and understanding user behaviors. Though effective, prevalent approaches never consider higher-order spatiotemporal connectivity within QoS data, thus suffering from inferior performance. To address this critical issue, this paper presents spatiotemporal graph convolutional network (GCN) that is equipped with the functionality of latent factorization of tensors (SGLFT). It is achieved by introducing three key innovations: 1) Proposing a tensor graph convolution based on the generalized tensor product technique for uniformly modeling the temporal and spatial patterns within dynamic user-service graphs; 2) Incorporating the built layer-wise graph convolution into tensor factorization for efficiently capturing the implied spatiotemporal high-order connectivity; and 3) Developing a node-level attention pooling mechanism to perceive feature differences among neighbors and across time slots. Theoretical derivations are conducted to demonstrate that the expressivity of the graph neural network proposed in this paper is evidently higher than that of vanilla GCNs. Empirical studies on eight large-scale testing cases arising from two real-world dynamic QoS datasets show that SGLFT substantially outperforms state-of-the-art QoS estimators regarding estimation accuracy for missing dynamic QoS data.
- Cloud service,
- data science,
- dynamic quality-of-service estimation,
- graph convolutional networks (GCNs),
- latent factorization of tensors,
- latent feature analysis,
- non-euclidean data,
- representation learning,
- tensor product

FullText(HTML)

¹ Supplementary Material of this paper can be found in link https://www.ieee-jas.com/article/doi/10.1109/JAS.2025.125750?pageType=en#Supplements

References(45)

References

[1]	Y. Wang, Y. Tian, J. Wang, Y. Cao, S. Li, and B. Tian, “Integrated inspection of QoM, QoP, and QoS for AOI industries in metaverses,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 12, pp. 2071–2078, Dec. 2022. doi: 10.1109/JAS.2022.106091
[2]	D. Wu, P. Zhang, Y. He, and X. Luo, “A double-space and double-norm ensembled latent factor model for highly accurate web service QoS prediction,” IEEE Trans. Serv. Comput., vol. 16, no. 2, pp. 802–814, Mar.–Apr. 2023. doi: 10.1109/TSC.2022.3178543
[3]	G. Zou, S. Wu, S. Hu, C. Cao, Y. Gan, B. Zhang, and Y. Chen, “NCRL: Neighborhood-based collaborative residual learning for adaptive QoS prediction,” IEEE Trans. Serv. Comput., vol. 16, no. 3, pp. 2030–2043, May–Jun. 2023.
[4]	W. J. Huang, P. Y. Zhang, Y. T. Chen, M. C. Zhou, Y. Al-Turki, and A. Abusorrah, “QoS prediction model of cloud services based on deep learning,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 3, pp. 564–566, Mar. 2022. doi: 10.1109/JAS.2021.1004392
[5]	F. Bi, T. He, Y. Xie, and X. Luo, “Two-stream graph convolutional network-incorporated latent feature analysis,” IEEE Trans. Serv. Comput., vol. 16, no. 4, pp. 3027–3042, Jul.–Aug. 2023. doi: 10.1109/TSC.2023.3241659
[6]	Y.-Y. Fanjiang, Y. Syu, and W.-L. Huang, “Time series QoS forecasting for web services using multi-predictor-based genetic programming,” IEEE Trans. Serv. Comput., vol. 15, no. 3, pp. 1423–1435, May–Jun. 2022. doi: 10.1109/TSC.2020.2994136
[7]	F. Bi, T. He, and X. Luo, “A fast nonnegative autoencoder-based approach to latent feature analysis on high-dimensional and incomplete data,” IEEE Trans. Serv. Comput., vol. 17, no. 3, pp. 733–746, May–Jun. 2024. doi: 10.1109/TSC.2023.3319713
[8]	K. Liu, F. Xue, X. He, D. Guo, and R. Hong, “Joint multi-grained popularity-aware graph convolution collaborative filtering for recommendation,” IEEE Trans. Comput. Soc. Syst., vol. 10, no. 1, pp. 72–83, Feb. 2023. doi: 10.1109/TCSS.2022.3151822
[9]	D. Wu, X. Luo, M. Shang, Y. He, G. Wang, and X. Wu, “A data-characteristic-aware latent factor model for web services QoS prediction,” IEEE Trans. Knowl. Data Eng., vol. 34, no. 6, pp. 2525–2538, Jun. 2022.
[10]	J. Hu, B. Hooi, S. Qian, Q. Fang, and C. Xu, “MGDCF: Distance learning via Markov graph diffusion for neural collaborative filtering,” IEEE Trans. Knowl. Data Eng., vol. 36, no. 7, pp. 3281–3296, Jul. 2024. doi: 10.1109/TKDE.2023.3348537
[11]	T. Zhu, L. Sun, and G. Chen, “Embedding disentanglement in graph convolutional networks for recommendation,” IEEE Trans. Knowl. Data Eng., vol. 35, no. 1, pp. 431–442, Jan. 2023. doi: 10.1109/tkde.2021.3087791
[12]	X. Luo, H. Wu, H. Yuan, and M. C. Zhou, “Temporal pattern-aware QoS prediction via biased non-negative latent factorization of tensors,” IEEE Trans. Cybern., vol. 50, no. 5, pp. 1798–1809, May 2020. doi: 10.1109/TCYB.2019.2903736
[13]	Y. Yuan, X. Luo, M. Shang, and Z. Wang, “A Kalman-filter-incorporated latent factor analysis model for temporally dynamic sparse data,” IEEE Trans. Cybern., vol. 53, no. 9, pp. 5788–5801, Sep. 2023. doi: 10.1109/TCYB.2022.3185117
[14]	R. Jiang, Z. Wang, J. Yong, P. Jeph, Q. Chen, Y. Kobayashi, X. Song, S. Fukushima, and T. Suzumura, “Spatio-temporal meta-graph learning for traffic forecasting,” in Proc. 37th AAAI Conf. Artificial Intelligence, Washington, USA, 2023, pp. 8078−8086.
[15]	A. Pareja, G. Domeniconi, J. Chen, T. Ma, T. Suzumura, H. Kanezashi, T. Kaler, T. B. Schardl, and C. E. Leiserson, “EvolveGCN: Evolving graph convolutional networks for dynamic graphs,” in Proc. 34th AAAI Conf. Artificial Intelligence, New York, USA, 2020, pp. 5363−5370.
[16]	J. Gao and B. Ribeiro, “On the equivalence between temporal and static equivariant graph representations,” in Proc. 39th Int. Conf. Machine Learning, Baltimore, USA, 2022, pp. 7052−7076.
[17]	J. Zhou, D. Ding, Z. Wu, and Y. Xiu, “Spatial context-aware time-series forecasting for QoS prediction,” IEEE Trans. Netw. Serv. Manag., vol. 20, no. 2, pp. 918–931, Jun. 2023. doi: 10.1109/TNSM.2023.3250512
[18]	Y. Sun, X. Jiang, Y. Hu, F. Duan, K. Guo, B. Wang, J. Gao, and B. Yin, “Dual dynamic spatial-temporal graph convolution network for traffic prediction,” IEEE Trans. Intell. Transp. Syst., vol. 23, no. 12, pp. 23680–23693, Dec. 2022. doi: 10.1109/TITS.2022.3208943
[19]	A. Cini, I. Marisca, F. M. Bianchi, and C. Alippi, “Scalable spatiotemporal graph neural networks,” in Proc. 37th AAAI Conf. Artificial Intelligence, Washington, USA, 2023, pp. 7218−7226.
[20]	W. Cong, S. Zhang, J. Kang, B. Yuan, H. Wu, X. Zhou, H. Tong, and M. Mahdavi, “Do we really need complicated model architectures for temporal networks?” in Proc. 11th Int. Conf. Learning Representations, Kigali, Rwanda, 2023, pp. 1−27.
[21]	M. Zhu, X. Wang, C. Shi, H. Ji, and P. Cui, “Interpreting and unifying graph neural networks with an optimization framework,” in Proc. Web Conf., Ljubljana, Slovenia, 2021, pp. 1215−1226.
[22]	A. Zhang, W. Ma, J. Zheng, X. Wang, and T.-S. Chua, “Robust collaborative filtering to popularity distribution shift,” ACM Trans. Inf. Syst., vol. 42, no. 3, Art. no. 80, May 2024. doi: 10.1145/3627159
[23]	T. Kong, T. Kim, J. Jeon, J. Choi, Y.-C. Lee, N. Park, and S.-W. Kim, “Linear, or non-linear, that is the question!” in Proc. 15th ACM Int. Conf. Web Search and Data Mining, Tempe, USA, 2022, pp. 517−525.
[24]	X. He, K. Deng, X. Wang, Y. Li, Y. D. Zhang, and M. Wang, “LightGCN: Simplifying and powering graph convolution network for recommendation,” in Proc. 43rd Int. ACM SIGIR Conf. Research and Development in Information Retrieval, Xi’an, China, 2020, pp. 639−648.
[25]	O. A. Malik, S. Ubaru, L. Horesh, M. E. Kilmer, and H. Avron, “Dynamic graph convolutional networks using the tensor M-product,” in Proc. SIAM Int. Conf. Data Mining, 2021, pp. 729−737.
[26]	K. Braman, “Third-order tensors as linear operators on a space of matrices,” Linear Algebra Appl., vol. 433, no. 7, pp. 1241–1253, Dec. 2010. doi: 10.1016/j.laa.2010.05.025
[27]	M. E. Kilmer, L. Horesh, H. Avron, and E. Newman, “Tensor-tensor algebra for optimal representation and compression of multiway data,” Proc. Natl. Acad. Sci. USA, vol. 118, no. 28, Art. no. e2015851118, Jul. 2021. doi: 10.1073/pnas.2015851118
[28]	N. Zeng, X. Li, P. Wu, H. Li, and X. Luo, “A novel tensor decomposition-based efficient detector for low-altitude aerial objects with knowledge distillation scheme,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 2, pp. 487–501, Feb. 2024. doi: 10.1109/JAS.2023.124029
[29]	T. Sun, C. Wang, H. Dong, Y. Zhou, and C. Guan, “A novel parameter-optimized recurrent attention network for pipeline leakage detection,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 4, pp. 1064–1076, Apr. 2023. doi: 10.1109/JAS.2023.123180
[30]	T. He, Y.-S. Ong, and L. Bai, “Learning conjoint attentions for graph neural nets,” in Proc. 35th Int. Conf. Neural Information Processing Systems, 2021, Art. no. 202.
[31]	K. Xu, W. Hu, J. Leskovec, and S. Jegelka, “How powerful are graph neural networks?” in Proc. 7th Int. Conf. Learning Representations, New Orleans, USA, 2019, pp. 1−17.
[32]	Q. Zhu, Q. Xiong, Z. Yang, and Y. Yu, “RGCNU: Recurrent graph convolutional network with uncertainty estimation for remaining useful life prediction,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 7, pp. 1640–1642, Jul. 2023. doi: 10.1109/JAS.2023.123369
[33]	J. Liu, C. Xu, C. Yin, W. Wu, and Y. Song, “K-core based temporal graph convolutional network for dynamic graphs,” IEEE Trans. Knowl. Data Eng., vol. 34, no. 8, pp. 3841–3853, Aug. 2022. doi: 10.1109/TKDE.2020.3033829
[34]	Y. Shin and Y. Yoon, “PGCN: Progressive graph convolutional networks for spatial–temporal traffic forecasting,” IEEE Trans. Intell. Transp. Syst., vol. 25, no. 7, pp. 7633–7644, Jul. 2024. doi: 10.1109/TITS.2024.3349565
[35]	T. He, Y. Liu, Y.-S. Ong, X. Wu, and X. Luo, “Polarized message-passing in graph neural networks,” Artif. Intell., vol. 331, Art. no. 104129, Jun. 2024. doi: 10.1016/j.artint.2024.104129
[36]	H. Zhou, T. He, Y.-S. Ong, G. Cong, and Q. Chen, “Differentiable clustering for graph attention,” IEEE Trans. Knowl. Data Eng., vol. 36, no. 8, pp. 3751–3764, Aug. 2024.
[37]	H. Zhou, W. Huang, Y. Chen, T. He, G. Cong, and Y.-S. Ong, “Road network representation learning with the third law of geography,” in Proc. 38th Int. Conf. Neural Information Processing Systems, Vancouver, Canada, 2024, Art. no. 376.
[38]	D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in Proc. 3rd Int. Conf. Learning Representations, San Diego, USA, 2015.
[39]	F. Bi, X. Luo, B. Shen, H. Dong, and Z. Wang, “Proximal alternating-direction-method-of-multipliers-incorporated nonnegative latent factor analysis,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 6, pp. 1388–1406, Jun. 2023. doi: 10.1109/JAS.2023.123474
[40]	F. Manessi, A. Rozza, and M. Manzo, “Dynamic graph convolutional networks,” Pattern Recognit., vol. 97, Art. no. 107000, Jan. 2020. doi: 10.1016/j.patcog.2019.107000
[41]	X. Wang, D. Lyu, M. Li, Y. Xia, Q. Yang, X. Wang, P. Cui, Y. Yang, B. Sun, and Z. Guo, “APAN: Asynchronous propagation attention network for real-time temporal graph embedding,” in Proc. Int. Conf. Management of Data, China, 2021, pp. 2628−2638.
[42]	M. Bhanu, J. Mendes-Moreira, and J. Chandra, “Embedding traffic network characteristics using tensor for improved traffic prediction,” IEEE Trans. Intell. Transp. Syst., vol. 22, no. 6, pp. 3359–3371, Jun. 2021. doi: 10.1109/TITS.2020.2984175
[43]	V. N. Ioannidis, A. S. Zamzam, G. B. Giannakis, and N. D. Sidiropoulos, “Coupled graphs and tensor factorization for recommender systems and community detection,” IEEE Trans. Knowl. Data Eng., vol. 33, no. 3, pp. 909–920, Mar. 2021.
[44]	X. Liu, M. Yan, L. Deng, G. Li, X. Ye, and D. Fan, “Sampling methods for efficient training of graph convolutional networks: A survey,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 2, pp. 205–234, Feb. 2022. doi: 10.1109/JAS.2021.1004311
[45]	R. Wang, Z. Zhou, K. Li, T. Zhang, L. Wang, X. Xu, and X. Liao, “Learning to branch in combinatorial optimization with graph pointer networks,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 1, pp. 157–169, Jan. 2024. doi: 10.1109/JAS.2023.124113