{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T16:38:13Z","timestamp":1784997493086,"version":"3.55.0"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s11432-023-4280-6","type":"journal-article","created":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T20:49:39Z","timestamp":1743281379000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A deep reinforcement learning model for large-scale traffic signal control based on graph meta-learning using local subgraphs"],"prefix":"10.1007","volume":"68","author":[{"given":"Zhicheng","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ya","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinde","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,3,24]]},"reference":[{"key":"4280_CR1","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/j.trd.2015.12.010","volume":"43","author":"M Grote","year":"2016","unstructured":"Grote M, Williams I, Preston J, et al. Including congestion effects in urban road traffic CO2 emissions modelling: do local government authorities have the right options? Transp Res Part D-Transp Environ, 2016, 43: 95\u2013106","journal-title":"Transp Res Part D-Transp Environ"},{"key":"4280_CR2","doi-asserted-by":"crossref","first-page":"2088","DOI":"10.1177\/0042098013505883","volume":"51","author":"M Sweet","year":"2014","unstructured":"Sweet M. Traffic congestion\u2019s economic impacts: evidence from US metropolitan regions. Urban Studies, 2014, 51: 2088\u20132110","journal-title":"Urban Studies"},{"key":"4280_CR3","doi-asserted-by":"crossref","first-page":"8662","DOI":"10.1109\/TITS.2021.3085021","volume":"23","author":"W Yue","year":"2022","unstructured":"Yue W, Li C, Chen Y, et al. What is the root cause of congestion in urban traffic networks: road infrastructure or signal control? IEEE Trans Intell Transp Syst, 2022, 23: 8662\u20138679","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"4280_CR4","unstructured":"Wei H, Zheng G, Gayah V, et al. A survey on traffic signal control methods. 2019. ArXiv:1904.08117"},{"key":"4280_CR5","volume-title":"SCATS, Sydney Co-Ordinated Adaptive Traffic System: A Traffic Responsive Method of Controlling Urban Traffic","author":"P R Lowrie","year":"1990","unstructured":"Lowrie P R. SCATS, Sydney Co-Ordinated Adaptive Traffic System: A Traffic Responsive Method of Controlling Urban Traffic. Darlinghurst: Roads and Traffic Authority NSW, 1990"},{"key":"4280_CR6","first-page":"190","volume":"23","author":"P Hunt","year":"1982","unstructured":"Hunt P, Robertson D, Bretherton R, et al. The scoot on-line traffic signal optimisation technique. Traffic Eng Control, 1982, 23: 190\u2013192","journal-title":"Traffic Eng Control"},{"key":"4280_CR7","volume-title":"Reinforcement Learning: An Introduction","author":"R S Sutton","year":"2018","unstructured":"Sutton R S, Barto A G. Reinforcement Learning: An Introduction. Cambridge: MIT Press, 2018"},{"key":"4280_CR8","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, et al. Human-level control through deep reinforcement learning. Nature, 2015, 518: 529\u2013533","journal-title":"Nature"},{"key":"4280_CR9","volume-title":"Proceedings of Advance Neural Information Processing Systems","author":"E Pol","year":"2016","unstructured":"Pol E, Oliehoek F A. Coordinated deep reinforcement learners for traffic light control. In: Proceedings of Advance Neural Information Processing Systems, 2016"},{"key":"4280_CR10","first-page":"1995","volume-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning","author":"Z Wang","year":"2016","unstructured":"Wang Z, Schaul T, Hessel M, et al. Dueling network architectures for deep reinforcement learning. In: Proceedings of the 33rd International Conference on International Conference on Machine Learning, 2016. 1995\u20132003"},{"key":"4280_CR11","first-page":"2094","volume-title":"Proceedings of the 30th AAAI Conference on Artificial Intelligence","author":"H van Hasselt","year":"2016","unstructured":"van Hasselt H, Guez A, Silver D. Deep reinforcement learning with double q-learning. In: Proceedings of the 30th AAAI Conference on Artificial Intelligence, 2016. 2094\u20132100"},{"key":"4280_CR12","unstructured":"Schaul T, Quan J, Antonoglou I, et al. Prioritized experience replay. 2015. ArXiv:1511.05952"},{"key":"4280_CR13","doi-asserted-by":"crossref","first-page":"1243","DOI":"10.1109\/TVT.2018.2890726","volume":"68","author":"X Liang","year":"2019","unstructured":"Liang X, Du X, Wang G, et al. A deep reinforcement learning network for traffic light cycle control. IEEE Trans Veh Technol, 2019, 68: 1243\u20131253","journal-title":"IEEE Trans Veh Technol"},{"key":"4280_CR14","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1007\/978-3-540-27868-9_4","volume-title":"Structural, Syntactic, and Statistical Pattern Recognition. Berlin: Springer","author":"F Scarselli","year":"2004","unstructured":"Scarselli F, Tsoi A C, Gori M, et al. Graphical-based learning environments for pattern recognition. In: Structural, Syntactic, and Statistical Pattern Recognition. Berlin: Springer, 2004. 42\u201356"},{"key":"4280_CR15","doi-asserted-by":"crossref","first-page":"7496","DOI":"10.1109\/TITS.2021.3070835","volume":"23","author":"F X Devailly","year":"2022","unstructured":"Devailly F X, Larocque D, Charlin L. IG-RL: inductive graph reinforcement learning for massive-scale traffic signal control. IEEE Trans Intell Transp Syst, 2022, 23: 7496\u20137507","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"4280_CR16","first-page":"20","volume":"1050","author":"P Velickovic","year":"2017","unstructured":"Velickovic P, Cucurull G, Casanova A, et al. Graph attention networks. Stat, 2017, 1050: 20","journal-title":"Stat"},{"key":"4280_CR17","doi-asserted-by":"crossref","first-page":"1913","DOI":"10.1145\/3357384.3357902","volume-title":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management","author":"H Wei","year":"2019","unstructured":"Wei H, Xu N, Zhang H, et al. CoLight: learning network-level cooperation for traffic signal control. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 2019. 1913\u20131922"},{"key":"4280_CR18","doi-asserted-by":"crossref","first-page":"6248","DOI":"10.1007\/s10489-022-03208-w","volume":"53","author":"L Yan","year":"2023","unstructured":"Yan L, Zhu L, Song K, et al. Graph cooperation deep reinforcement learning for ecological urban traffic signal control. Appl Intell, 2023, 53: 6248\u20136265","journal-title":"Appl Intell"},{"key":"4280_CR19","doi-asserted-by":"crossref","first-page":"1153","DOI":"10.1609\/aaai.v34i01.5467","volume":"34","author":"X Zang","year":"2020","unstructured":"Zang X, Yao H, Zheng G, et al. MetaLight: value-based meta-reinforcement learning for traffic signal control. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2020. 34: 1153\u20131160","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"4280_CR20","doi-asserted-by":"crossref","first-page":"109166","DOI":"10.1016\/j.knosys.2022.109166","volume":"250","author":"M Wang","year":"2022","unstructured":"Wang M, Wu L, Li M, et al. Meta-learning based spatial-temporal graph attention network for traffic signal control. Knowledge-Based Syst, 2022, 250: 109166","journal-title":"Knowledge-Based Syst"},{"key":"4280_CR21","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1007\/978-1-4614-6243-9_2","volume-title":"Proceedings of Advances in Dynamic Network Modeling in Complex Transportation Systems","author":"P Varaiya","year":"2013","unstructured":"Varaiya P. The max-pressure controller for arbitrary networks of signalized intersections. In: Proceedings of Advances in Dynamic Network Modeling in Complex Transportation Systems, 2013. 27\u201366"},{"key":"4280_CR22","unstructured":"Zhang L, Wu Q, Deng J. AttentionLight: rethinking queue length and attention mechanism for traffic signal control. 2021. ArXiv:2201.00006"},{"key":"4280_CR23","doi-asserted-by":"crossref","first-page":"104048","DOI":"10.1016\/j.artint.2023.104048","volume":"326","author":"C Bai","year":"2024","unstructured":"Bai C, Wang L, Hao J, et al. Pessimistic value iteration for multi-task data sharing in offline reinforcement learning. Artif Intelligence, 2024, 326: 104048","journal-title":"Artif Intelligence"},{"key":"4280_CR24","unstructured":"He H, Bai C, Xu K, et al. Diffusion model is an effective planner and data synthesizer for multi-task reinforcement learning. 2023. ArXiv:2305.18459"},{"key":"4280_CR25","doi-asserted-by":"crossref","first-page":"8954","DOI":"10.1109\/TNNLS.2022.3217189","volume":"35","author":"C Bai","year":"2024","unstructured":"Bai C, Xiao T, Zhu Z, et al. Monotonic quantile network for worst-case offline reinforcement learning. IEEE Trans Neural Netw Learn Syst, 2024, 35: 8954\u20138968","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"4280_CR26","unstructured":"Xu K, Bai C, Ma X, et al. Cross-domain policy adaptation via value-guided data filtering. 2023. ArXiv:2305.17625"},{"key":"4280_CR27","doi-asserted-by":"crossref","first-page":"8762","DOI":"10.1109\/TNNLS.2023.3236361","volume":"35","author":"J Hao","year":"2024","unstructured":"Hao J, Yang T, Tang H, et al. Exploration in deep reinforcement learning: from single-agent to multiagent domain. IEEE Trans Neural Netw Learn Syst, 2024, 35: 8762\u20138782","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"4280_CR28","first-page":"5883","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"J Sun","year":"2020","unstructured":"Sun J, Zhang T, Xie X, et al. Stealthy and efficient adversarial attacks against deep reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2020. 5883\u20135891"},{"key":"4280_CR29","doi-asserted-by":"crossref","first-page":"1892","DOI":"10.1360\/SSI-2023-0010","volume":"53","author":"J Y Hao","year":"2023","unstructured":"Hao J Y, Shao K, Li K, et al. Research and applications of game intelligence (in Chinese). Sci Sin Inform, 2023, 53: 1892\u20131923","journal-title":"Sci Sin Inform"},{"key":"4280_CR30","first-page":"1","volume-title":"Proceedings of the 23rd International Conference on Intelligent Transportation Systems (ITSC)","author":"X Li","year":"2020","unstructured":"Li X, Guo Z, Dai X, et al. Deep imitation learning for traffic signal control and operations based on graph convolutional neural networks. In: Proceedings of the 23rd International Conference on Intelligent Transportation Systems (ITSC), 2020. 1\u20136"},{"key":"4280_CR31","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1109\/JAS.2016.7508798","volume":"3","author":"L Li","year":"2016","unstructured":"Li L, Lv Y, Wang F Y. Traffic signal timing via deep reinforcement learning. IEEE CAA J Autom Sin, 2016, 3: 247\u2013254","journal-title":"IEEE CAA J Autom Sin"},{"key":"4280_CR32","doi-asserted-by":"crossref","first-page":"2496","DOI":"10.1145\/3219819.3220096","volume-title":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","author":"H Wei","year":"2018","unstructured":"Wei H, Zheng G, Yao H, et al. IntelliLight: a reinforcement learning approach for intelligent traffic light control. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018. 2496\u20132505"},{"key":"4280_CR33","first-page":"3414","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"C Chen","year":"2020","unstructured":"Chen C, Wei H, Xu N, et al. Toward a thousand lights: decentralized deep reinforcement learning for large-scale traffic signal control. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2020. 3414\u20133421"},{"key":"4280_CR34","doi-asserted-by":"crossref","first-page":"25157","DOI":"10.1109\/TITS.2022.3173490","volume":"23","author":"C Zhang","year":"2022","unstructured":"Zhang C, Tian Y, Zhang Z, et al. Neighborhood cooperative multiagent reinforcement learning for adaptive traffic signal control in epidemic regions. IEEE Trans Intell Transp Syst, 2022, 23: 25157\u201325168","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"4280_CR35","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1109\/TITS.2022.3216203","volume":"24","author":"W Zhang","year":"2023","unstructured":"Zhang W, Yan C, Li X, et al. Distributed signal control of arterial corridors using multi-agent deep reinforcement learning. IEEE Trans Intell Transp Syst, 2023, 24: 178\u2013190","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"4280_CR36","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1109\/TFUZZ.2022.3214001","volume":"31","author":"B Fang","year":"2023","unstructured":"Fang B, Zheng C, Wang H, et al. Two-stream fused fuzzy deep neural network for multiagent learning. IEEE Trans Fuzzy Syst, 2023, 31: 511\u2013520","journal-title":"IEEE Trans Fuzzy Syst"},{"key":"4280_CR37","doi-asserted-by":"crossref","first-page":"1187","DOI":"10.1109\/TVT.2021.3069921","volume":"71","author":"A Boukerche","year":"2022","unstructured":"Boukerche A, Zhong D, Sun P. A novel reinforcement learning-based cooperative traffic signal system through max-pressure control. IEEE Trans Veh Technol, 2022, 71: 1187\u20131198","journal-title":"IEEE Trans Veh Technol"},{"key":"4280_CR38","unstructured":"Wu Q, Zhang L, Shen J, et al. Efficient pressure: improving efficiency for signalized intersections. 2021. ArXiv:2112.02336"},{"key":"4280_CR39","first-page":"26645","volume-title":"Proceedings of International Conference on Machine Learning","author":"L Zhang","year":"2022","unstructured":"Zhang L, Wu Q, Shen J, et al. Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal control. In: Proceedings of International Conference on Machine Learning, 2022. 26645\u201326654"},{"key":"4280_CR40","unstructured":"Bose A J, Jain A, Molino P, et al. Meta-graph: few shot link prediction via meta learning. 2019. ArXiv:1912.09867"},{"key":"4280_CR41","unstructured":"Xu K, Hu W, Leskovec J, et al. How powerful are graph neural networks? 2018. ArXiv:1810.00826"},{"key":"4280_CR42","first-page":"5862","volume":"33","author":"K Huang","year":"2020","unstructured":"Huang K, Zitnik M. Graph meta learning via local subgraphs. In: Proceedings of Advance Neural Information Processing Systems, 2020. 33: 5862\u20135874","journal-title":"Proceedings of Advance Neural Information Processing Systems"},{"key":"4280_CR43","first-page":"30","volume-title":"Proceedings of Advance Neural Information Processing Systems","author":"W Hamilton","year":"2017","unstructured":"Hamilton W, Ying Z, Leskovec J. Inductive representation learning on large graphs. In: Proceedings of Advance Neural Information Processing Systems, 2017, 30"},{"key":"4280_CR44","unstructured":"Kingma D P, Ba J. Adam: a method for stochastic optimization. 2014. ArXiv:1412.6980"},{"key":"4280_CR45","doi-asserted-by":"crossref","first-page":"3620","DOI":"10.1145\/3308558.3314139","volume-title":"Proceedings of World Wide Web Conference","author":"H Zhang","year":"2019","unstructured":"Zhang H, Feng S, Liu C, et al. CityFlow: a multi-agent reinforcement learning environment for large scale city traffic scenario. In: Proceedings of World Wide Web Conference, 2019. 3620\u20133624"},{"key":"4280_CR46","unstructured":"Wang M, Zheng D, Ye Z, et al. Deep graph library: a graph-centric, highly-performant package for graph neural networks. 2019. ArXiv:1909.01315"},{"key":"4280_CR47","series-title":"Technical Report","volume-title":"Traffic Signal Timing Manual","author":"P Koonce","year":"2008","unstructured":"Koonce P, Rodegerdts L, Lee K, et al. Traffic Signal Timing Manual. Technical Report, FHWA-HOP-08-024, Kittelson & Associates, Inc., 2008"},{"key":"4280_CR48","unstructured":"Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks. 2016. ArXiv:1609.02907"},{"key":"4280_CR49","unstructured":"Li B, Tang H, Zheng Y, et al. HyAR: addressing discrete-continuous action reinforcement learning via hybrid action representation. 2021. ArXiv:2109.05490"},{"key":"4280_CR50","unstructured":"Li P, Tang H, Yang T, et al. PMIC: improving multi-agent reinforcement learning with progressive mutual information collaboration. 2022. ArXiv:2203.08553"},{"key":"4280_CR51","unstructured":"Yang Y, Hao J, Liao B, et al. Qatten: a general framework for cooperative multiagent reinforcement learning. 2020. ArXiv:2002.03939"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-023-4280-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-023-4280-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-023-4280-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T20:51:45Z","timestamp":1743281505000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-023-4280-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,24]]},"references-count":51,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["4280"],"URL":"https:\/\/doi.org\/10.1007\/s11432-023-4280-6","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,24]]},"assertion":[{"value":"8 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 March 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 March 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"172203"}}