{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:15:28Z","timestamp":1783152928469,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","funder":[{"name":"NSF China","award":["62372288, W2412089"],"award-info":[{"award-number":["62372288, W2412089"]}]},{"name":"Fund","award":["USCAST2023-13"],"award-info":[{"award-number":["USCAST2023-13"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792331","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:39Z","timestamp":1775771679000},"page":"947-958","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Breaking the Scalability Barrier in Constrained Graph-Based Networked Control via Decision-Focused Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7008-7629","authenticated-orcid":false,"given":"Zhaoxing","family":"Yang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8678-7340","authenticated-orcid":false,"given":"Yuchen","family":"Guo","sequence":"additional","affiliation":[{"name":"Shanghai Institute of Satellite Engineering, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4109-6888","authenticated-orcid":false,"given":"Wenlong","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Institute of Satellite Engineering, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7007-6110","authenticated-orcid":false,"given":"Guiyun","family":"Fan","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5178-7198","authenticated-orcid":false,"given":"Haiming","family":"Jin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9266-3044","authenticated-orcid":false,"given":"Linghe","family":"Kong","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Andrzej Ruszczy?ski Alexander Shapiro Darinka Dentcheva. 2021. Lectures on Stochastic Programming: Modeling and Theory. SIAM.","DOI":"10.1137\/1.9781611976595.ch1"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"e_1_3_2_1_3_1","unstructured":"Karl J. Astrom. 1971. Introduction to Stochastic Control Theory. Elsevier."},{"key":"e_1_3_2_1_4_1","volume-title":"Risk-constrained reinforcement learning with percentile risk criteria. JMLR","author":"Chow Yinlam","year":"2018","unstructured":"Yinlam Chow, Mohammad Ghavamzadeh, Lucas Janson, and Marco Pavone. 2018. Risk-constrained reinforcement learning with percentile risk criteria. JMLR (2018)."},{"key":"e_1_3_2_1_5_1","volume-title":"1: User's Manual for CPLEX","author":"Cplex IBM ILOG","year":"2009","unstructured":"IBM ILOG Cplex. 2009. V12. 1: User's Manual for CPLEX. International Business Machines Corporation (2009)."},{"key":"e_1_3_2_1_6_1","volume-title":"NAN DING, Michael Thompson, Makoto Suminaka, Marcus Greiff, and John Subosits.","author":"Djeumou Franck","year":"2024","unstructured":"Franck Djeumou, Thomas Jonathan Lew, NAN DING, Michael Thompson, Makoto Suminaka, Marcus Greiff, and John Subosits. 2024. One Model to Drift Them All: Physics-Informed Conditional Diffusion Model for Driving at the Limits. In CoRL."},{"key":"e_1_3_2_1_7_1","volume-title":"Elmachtoub and Paul Grigas","author":"Adam","year":"2017","unstructured":"Adam N. Elmachtoub and Paul Grigas. 2017. Smart ''Predict, then Optimize''. ArXiv (2017)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"L. R. Ford and D. R. Fulkerson. 1956. Maximal Flow Through a Network. Canadian Journal of Mathematics (1956).","DOI":"10.4153\/CJM-1956-045-5"},{"key":"e_1_3_2_1_9_1","volume-title":"Constructing Maximal Dynamic Flows from Static Flows. Operations Research","author":"Ford Lester Randolph","year":"1958","unstructured":"Lester Randolph Ford and Delbert Ray Fulkerson. 1958. Constructing Maximal Dynamic Flows from Static Flows. Operations Research (1958)."},{"key":"e_1_3_2_1_10_1","unstructured":"Daniele Gammelli James Harrison Kaidi Yang Marco Pavone Filipe Rodrigues and Francisco C Pereira. 2023. Graph Reinforcement Learning for Network Control via Bi-Level Optimization. In ICML."},{"key":"e_1_3_2_1_11_1","unstructured":"Gurobi Optimization LLC. 2023. Gurobi Optimizer Reference Manual. https:\/\/www.gurobi.com"},{"key":"e_1_3_2_1_12_1","volume-title":"Introduction To Operations Research","author":"Hillier Frederick","unstructured":"Frederick Hillier and Gerald Lieberman. 1969. Introduction To Operations Research. McGraw-Hill Professional."},{"key":"e_1_3_2_1_13_1","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. In NeurIPS."},{"key":"e_1_3_2_1_14_1","volume-title":"Flows in Networks","author":"Fulkerson Lester Randolph Ford D. R.","unstructured":"D. R. Fulkerson Lester Randolph Ford. 1962. Flows in Networks. Princeton University Press."},{"key":"e_1_3_2_1_15_1","unstructured":"Yuanjie Li Hewu Li Wei Liu Lixin Liu Wei Zhao Yimei Chen Jianping Wu Qian Wu Jun Liu Zeqi Lai and Han Qiu. 2023. A Networking Perspective on Starlink's Self-Driving LEO Mega-Constellation. In MobiCom."},{"key":"e_1_3_2_1_16_1","volume-title":"Decision-focused learning: Foundations, state of the art, benchmark and future opportunities. JAIR","author":"Mandi Jayanta","year":"2024","unstructured":"Jayanta Mandi, James Kotary, Senne Berden, Maxime Mulamba, Victor Bucarey, Tias Guns, and Ferdinando Fioretto. 2024. Decision-focused learning: Foundations, state of the art, benchmark and future opportunities. JAIR (2024)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/9781119815068"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Aaryan Singhal Daniele Gammelli Justin Luke Karthik Gopalakrishnan Dominik Helmreich and Marco Pavone. 2024. Real-time Control of Electric Autonomous Mobility-on-Demand Systems via Graph Reinforcement Learning. In ECC.","DOI":"10.23919\/ECC64448.2024.10591098"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Bill Tao Maleeha Masood Indranil Gupta and Deepak Vasisht. 2023. Transmitting Fast and Slow: Scheduling Satellite Traffic through Space and Time. In MobiCom.","DOI":"10.1145\/3570361.3592521"},{"key":"e_1_3_2_1_20_1","unstructured":"B. Van Roy D.P. Bertsekas Y. Lee and J.N. Tsitsiklis. 1997. A neuro-dynamic programming approach to retailer inventory management. In CDC."},{"key":"e_1_3_2_1_21_1","unstructured":"Kai Wang Sanket Shah Haipeng Chen Andrew Perrault Finale Doshi-Velez and Milind Tambe. 2021. Learning mdps from features: Predict-then-optimize for sequential decision making by reinforcement learning. In NeurIPS."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Kai Wang Shresth Verma Aditya Mate Sanket Shah Aparna Taneja Neha Madhiwalla Aparna Hegde and Milind Tambe. 2023. Scalable Decision-Focused Learning in Restless Multi-Armed Bandits with Application to Maternal and Child Health. In AAAI.","DOI":"10.1609\/aaai.v37i10.26431"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Long Wei Peiyan Hu Ruiqi Feng Haodong Feng Yixuan Du Tao Zhang Rui Wang Yue Wang Zhi-Ming Ma and Tailin Wu. 2024. DiffPhyCon: A Generative Approach to Control Complex Physical Systems. In NeurIPS.","DOI":"10.52202\/079017-0134"},{"key":"e_1_3_2_1_24_1","volume-title":"Teal: Learning-Accelerated Optimization of WAN Traffic Engineering. In SIGCOMM.","author":"Xu Zhiying","year":"2023","unstructured":"Zhiying Xu, Francis Y. Yan, Rachee Singh, Justin T. Chiu, Alexander M. Rush, and Minlan Yu. 2023. Teal: Learning-Accelerated Optimization of WAN Traffic Engineering. In SIGCOMM."},{"key":"e_1_3_2_1_25_1","volume":"202","author":"Yang Qisong","unstructured":"Qisong Yang, Thiago D. Sim\u00e3o, Simon H Tindemans, and Matthijs T. J. Spaan. 2021. WCSAC: Worst-Case Soft Actor Critic for Safety-Constrained Reinforcement Learning. In AAAI.","journal-title":"J. Spaan."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Zhaoxing Yang Haiming Jin Yao Tang and Guiyun Fan. 2024. Risk-Aware Constrained Reinforcement Learning with Non-Stationary Policies. In AAMAS.","DOI":"10.65109\/ZRHO4945"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792331","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:19:33Z","timestamp":1783149573000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792331"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":26,"alternative-id":["10.1145\/3774904.3792331","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792331","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}