{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T22:37:28Z","timestamp":1778625448901,"version":"3.51.4"},"reference-count":57,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2023,7,28]],"date-time":"2023-07-28T00:00:00Z","timestamp":1690502400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62076251"],"award-info":[{"award-number":["62076251"]}]},{"name":"National Natural Science Foundation of China","award":["KYJBJKQTZK23003"],"award-info":[{"award-number":["KYJBJKQTZK23003"]}]},{"name":"Research and Application of Time Series and Spatio-Temporal Sequences in Multi-Task Learning","award":["62076251"],"award-info":[{"award-number":["62076251"]}]},{"name":"Research and Application of Time Series and Spatio-Temporal Sequences in Multi-Task Learning","award":["KYJBJKQTZK23003"],"award-info":[{"award-number":["KYJBJKQTZK23003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Accurate time series forecasting is of great importance in real-world scenarios such as health care, transportation, and finance. Because of the tendency, temporal variations, and periodicity of the time series data, there are complex and dynamic dependencies among its underlying features. In time series forecasting tasks, the features learned by a specific task at the current time step (such as predicting mortality) are related to the features of historical timesteps and the features of adjacent timesteps of related tasks (such as predicting fever). Therefore, capturing dynamic dependencies in data is a challenging problem for learning accurate future prediction behavior. To address this challenge, we propose a cross-timestep feature-sharing multi-task time series forecasting model that can capture global and local dynamic dependencies in time series data. Initially, the global dynamic dependencies of features within each task are captured through a self-attention mechanism. Furthermore, an adaptive sparse graph structure is employed to capture the local dynamic dependencies inherent in the data, which can explicitly depict the correlation between features across timesteps and tasks. Lastly, the cross-timestep feature sharing between tasks is achieved through a graph attention mechanism, which strengthens the learning of shared features that are strongly correlated with a single task. It is beneficial for improving the generalization performance of the model. Our experimental results demonstrate that our method is significantly competitive compared to baseline methods.<\/jats:p>","DOI":"10.3390\/e25081136","type":"journal-article","created":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T01:26:40Z","timestamp":1690766800000},"page":"1136","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Multi-Task Time Series Forecasting Based on Graph Neural Networks"],"prefix":"10.3390","volume":"25","author":[{"given":"Xiao","family":"Han","sequence":"first","affiliation":[{"name":"Command Control Engineering College, Army Engineering University of PLA, Nanjing 210007, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongjie","family":"Huang","sequence":"additional","affiliation":[{"name":"Command Control Engineering College, Army Engineering University of PLA, Nanjing 210007, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhisong","family":"Pan","sequence":"additional","affiliation":[{"name":"Command Control Engineering College, Army Engineering University of PLA, Nanjing 210007, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"Command Control Engineering College, Army Engineering University of PLA, Nanjing 210007, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yahao","family":"Hu","sequence":"additional","affiliation":[{"name":"Command Control Engineering College, Army Engineering University of PLA, Nanjing 210007, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gengyou","family":"Lin","sequence":"additional","affiliation":[{"name":"Command Control Engineering College, Army Engineering University of PLA, Nanjing 210007, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,7,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Ullmann, D., Taran, O., and Voloshynovskiy, S. (2023). Multivariate Time Series Information Bottleneck. Entropy, 25.","DOI":"10.3390\/e25050831"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Han, L., Du, B., Sun, L., Fu, Y., Lv, Y., and Xiong, H. (2021, January 14\u201318). Dynamic and Multi-faceted Spatio-temporal Deep Learning for Traffic Speed Forecasting. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Singapore.","DOI":"10.1145\/3447548.3467275"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Jiang, W., Zhu, G., Shen, Y., Xie, Q., Ji, M., and Yu, Y. (2022). An Empirical Mode Decomposition Fuzzy Forecast Model for Air Quality. Entropy, 24.","DOI":"10.3390\/e24121803"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Jin, X.B., Wang, Z.Y., Kong, J.L., Bai, Y.T., Su, T.L., Ma, H.J., and Chakrabarti, P. (2023). Deep Spatio-Temporal Graph Network with Self-Optimization for Air Quality Prediction. Entropy, 25.","DOI":"10.3390\/e25020247"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Chen, C.W.S., and Chiu, L.M. (2021). Ordinal Time Series Forecasting of the Air Quality Index. Entropy, 23.","DOI":"10.3390\/e23091167"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Clark, S.R., Pagendam, D., and Ryan, L. (2022). Forecasting Multiple Groundwater Time Series with Local and Global Deep Learning Networks. Int. J. Environ. Res. Public Health, 19.","DOI":"10.3390\/ijerph19095091"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1007\/978-3-642-38326-7_34","article-title":"Clinical Time Series Prediction with a Hierarchical Dynamical System","volume":"Volume 7885","author":"Hutchison","year":"2013","journal-title":"Artificial Intelligence in Medicine"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zhou, M., Zhang, Y., Liu, T., Yang, Y., and Yang, P. (2022, January 17\u201321). Multi-Task Learning with Adaptive Global Temporal Structure for Predicting Alzheimer\u2019s Disease Progression. Proceedings of the 31st ACM International Conference on Information & Knowledge Management, Atlanta, GA, USA.","DOI":"10.1145\/3511808.3557406"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Liapis, C.M., Karanikola, A., and Kotsiantis, S. (2021). A Multi-Method Survey on the Use of Sentiment Analysis in Multivariate Financial Time Series Forecasting. Entropy, 23.","DOI":"10.3390\/e23121603"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Box, G.E.P. (2008). Time Series Analysis, John Wiley and Sons.","DOI":"10.1002\/9781118619193"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"961","DOI":"10.1016\/S0893-6080(05)80092-9","article-title":"Forecasting the Behavior of Multivariate Time Series Using Neural Networks","volume":"5","author":"Charkraborty","year":"1992","journal-title":"Neural Netw."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"710","DOI":"10.1016\/j.energy.2017.12.156","article-title":"A Regional Hybrid GOA-SVM Model Based on Similar Day Approach for Short-Term Load Forecasting in Assam, India","volume":"145","author":"Barman","year":"2018","journal-title":"Energy"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_14","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017). Attention Is All You Need. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Huang, S., Wang, D., Wu, X., and Tang, A. (2019, January 3\u20137). DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting. Proceedings of the 28th ACM International Conference on Information and Knowledge Management, Beijing China.","DOI":"10.1145\/3357384.3358132"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1748","DOI":"10.1016\/j.ijforecast.2021.03.012","article-title":"Temporal Fusion Transformers for Interpretable Multi-Horizon Time Series Forecasting","volume":"37","author":"Lim","year":"2021","journal-title":"Int. J. Forecast."},{"key":"ref_17","first-page":"55865609","article-title":"A Survey on Multi-Task Learning","volume":"34","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1038\/s41597-019-0103-9","article-title":"Multitask Learning and Benchmarking with Clinical Time Series Data","volume":"6","author":"Harutyunyan","year":"2019","journal-title":"Sci. Data"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1109\/TBME.2014.2351376","article-title":"Multitask Gaussian Processes for Multivariate Physiological Time-Series Analysis","volume":"62","author":"Durichen","year":"2015","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The Graph Neural Network Model","volume":"20","author":"Scarselli","year":"2009","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"117921","DOI":"10.1016\/j.eswa.2022.117921","article-title":"Graph Neural Network for Traffic Forecasting: A Survey","volume":"207","author":"Jiang","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_22","unstructured":"Kipf, T.N., and Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. arXiv."},{"key":"ref_23","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., and Bengio, Y. (2018). Graph Attention Networks. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Yin, X., Li, F., Wu, G., Wang, P., Shen, Y., Qi, H., and Yin, B. (2021, January 14\u201316). STNN: A Spatial-Temporal Graph Neural Network for Traffic Prediction. Proceedings of the 2021 IEEE 27th International Conference on Parallel and Distributed Systems (ICPADS), Beijing, China.","DOI":"10.1109\/ICPADS53394.2021.00024"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"You, Y., Zhang, L., Tao, P., Liu, S., and Chen, L. (2022). Spatiotemporal Transformer Neural Network for Time-Series Forecasting. Entropy, 24.","DOI":"10.3390\/e24111651"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Han, J., Liu, H., Zhu, H., Xiong, H., and Dou, D. (2021). Joint Air Quality and Weather Prediction Based on Multi-Adversarial Spatiotemporal Networks. arXiv.","DOI":"10.1609\/aaai.v35i5.16529"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Wang, D., Zhang, J., Cao, W., Li, J., and Zheng, Y. (2018, January 2\u20137). When Will You Arrive? Estimating Travel Time Based on Deep Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.","DOI":"10.1609\/aaai.v32i1.11877"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/j.asoc.2019.03.039","article-title":"MultiTL-KELM: A Multi-Task Learning Algorithm for Multi-Step-Ahead Time Series Prediction","volume":"79","author":"Ye","year":"2019","journal-title":"Appl. Soft Comput."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Cirstea, R.G., Micu, D.V., Muresan, G.M., Guo, C., and Yang, B. (2018). Correlated Time Series Forecasting Using Deep Neural Networks: A Summary of Results. arXiv.","DOI":"10.1145\/3269206.3269310"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Chen, Z., E, J., Zhang, X., Sheng, H., and Cheng, X. (2020, January 17\u201320). Multi-Task Time Series Forecasting With Shared Attention. Proceedings of the 2020 International Conference on Data Mining Workshops (ICDMW), Sorrento, Italy.","DOI":"10.1109\/ICDMW51313.2020.00132"},{"key":"ref_31","first-page":"9081","article-title":"Clinical Risk Prediction with Temporal Probabilistic Asymmetric Multi-Task Learning","volume":"35","author":"Nguyen","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Li, Y., Fu, K., Wang, Z., Shahabi, C., Ye, J., and Liu, Y. (2018, January 19\u201323). Multi-Task Representation Learning for Travel Time Estimation. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, UK.","DOI":"10.1145\/3219819.3220033"},{"key":"ref_33","unstructured":"Seo, Y., Defferrard, M., Vandergheynst, P., and Bresson, X. (2016). Structured Sequence Modeling with Graph Convolutional Recurrent Networks. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Yu, B., Yin, H., and Zhu, Z. (2018). Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting. arXiv.","DOI":"10.24963\/ijcai.2018\/505"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"3848","DOI":"10.1109\/TITS.2019.2935152","article-title":"T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction","volume":"21","author":"Zhao","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Wu, T., Chen, F., and Wan, Y. (2018, January 20\u201322). Graph Attention LSTM Network: A New Model for Traffic Flow Forecasting. Proceedings of the 2018 5th International Conference on Information Science and Control Engineering (ICISCE), Zhengzhou, China.","DOI":"10.1109\/ICISCE.2018.00058"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"7592","DOI":"10.1109\/TII.2022.3211330","article-title":"TC-GATN: Temporal Causal Graph Attention Networks With Nonlinear Paradigm for Multivariate Time Series Forecasting in Industrial Processes","volume":"19","author":"Li","year":"2022","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1016\/j.ins.2022.04.045","article-title":"Graph Correlated Attention Recurrent Neural Network for Multivariate Time Series Forecasting","volume":"606","author":"Geng","year":"2022","journal-title":"Inf. Sci."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"20200209","DOI":"10.1098\/rsta.2020.0209","article-title":"Time Series Forecasting With Deep Learning: A Survey","volume":"379","author":"Lim","year":"2021","journal-title":"Philos. Trans. R. Soc. A Math. Phys. Eng. Sci."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Salinas, D., Flunkert, V., and Gasthaus, J. (2019). DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks. arXiv.","DOI":"10.1016\/j.ijforecast.2019.07.001"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Qin, Y., Song, D., Chen, H., Cheng, W., Jiang, G., and Cottrell, G. (2017). A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction. arXiv.","DOI":"10.24963\/ijcai.2017\/366"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Yin, X., Han, Y., Sun, H., Xu, Z., Yu, H., and Duan, X. (2020, January 7\u201310). A Multivariate Time Series Prediction Schema Based on Multi-attention in Recurrent Neural Network. Proceedings of the 2020 IEEE Symposium on Computers and Communications (ISCC), Rennes, France.","DOI":"10.1109\/ISCC50000.2020.9219721"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Huang, L., Mao, F., Zhang, K., and Li, Z. (2022). Spatial-Temporal Convolutional Transformer Network for Multivariate Time Series Forecasting. Sensors, 22.","DOI":"10.3390\/s22030841"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Song, H., Rajan, D., Thiagarajan, J.J., and Spanias, A. (2017). Attend and Diagnose: Clinical Time Series Analysis Using Attention Models. arXiv.","DOI":"10.1609\/aaai.v32i1.11635"},{"key":"ref_45","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., and Bengio, Y. (2016). Show, Attend and Tell: Neural Image Caption Generation with Visual Attention. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., and Zhang, W. (2021). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. arXiv.","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref_47","unstructured":"Li, S., Jin, X., Xuan, Y., Zhou, X., Chen, W., Wang, Y.X., and Yan, X. (2020). Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting. arXiv."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"160035","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a Freely Accessible Critical Care Database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci. Data"},{"key":"ref_49","unstructured":"Citi, L., and Barbieri, R. (2012, January 9\u201312). PhysioNet 2012 Challenge: Predicting Mortality of ICU Patients Using a Cascaded SVM-GLM Paradigm. Proceedings of the 2012 Computing in Cardiology, Krakow, Poland."},{"key":"ref_50","unstructured":"Che, Z., Purushotham, S., Cho, K., Sontag, D., and Liu, Y. (2016). Recurrent Neural Networks for Multivariate Time Series with Missing Values. arXiv."},{"key":"ref_51","unstructured":"Johnson, A.E.W., Pollard, T.J., and Mark, R.G. (2017, January 18\u201319). Reproducibility in Critical Care: A Mortality Prediction Case Study. Proceedings of the 2nd Machine Learning for Healthcare Conference, Boston, MA, USA."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Pirracchio, R. (2016). Mortality Prediction in the ICU Based on MIMIC-II Results from the Super ICU Learner Algorithm (SICULA) Project, Springer International Publishing.","DOI":"10.1007\/978-3-319-43742-2_20"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Purushotham, S., Meng, C., Che, Z., and Liu, Y. (2017). Benchmark of Deep Learning Models on Large Healthcare MIMIC Datasets. arXiv.","DOI":"10.1016\/j.jbi.2018.04.007"},{"key":"ref_54","unstructured":"Choi, E., Bahadori, M.T., Kulas, J.A., Schuetz, A., Stewart, W.F., and Sun, J. (2017). RETAIN: An Interpretable Predictive Model for Healthcare Using Reverse Time Attention Mechanism. arXiv."},{"key":"ref_55","unstructured":"Heo, J., Lee, H.B., Kim, S., Lee, J., Kim, K.J., Yang, E., and Hwang, S.J. (2018). Uncertainty-Aware Attention for Reliable Interpretation and Prediction. arXiv."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Ma, L., Gao, J., Wang, Y., Zhang, C., Wang, J., Ruan, W., Tang, W., Gao, X., and Ma, X. (2019). AdaCare: Explainable Clinical Health Status Representation Learning via Scale-Adaptive Feature Extraction and Recalibration. arXiv.","DOI":"10.1609\/aaai.v34i01.5427"},{"key":"ref_57","unstructured":"Lee, H.B., Yang, E., and Hwang, S.J. (2018). Deep Asymmetric Multi-task Feature Learning. arXiv."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/8\/1136\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:21:52Z","timestamp":1760127712000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/8\/1136"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,28]]},"references-count":57,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2023,8]]}},"alternative-id":["e25081136"],"URL":"https:\/\/doi.org\/10.3390\/e25081136","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,28]]}}}