{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:39:36Z","timestamp":1766219976884,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","funder":[{"name":"National Key R&D Program of China","award":["No. 2023YFB4502400"],"award-info":[{"award-number":["No. 2023YFB4502400"]}]},{"name":"Fundamental Research Funds for the Central Universities","award":["YG2022QN039"],"award-info":[{"award-number":["YG2022QN039"]}]},{"name":"China NSF","award":["62322206"],"award-info":[{"award-number":["62322206"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1145\/3754598.3754610","type":"proceedings-article","created":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:34:32Z","timestamp":1766219672000},"page":"511-520","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Joint Prediction and Matching for Computing Resource Exchange Platforms"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3054-5472","authenticated-orcid":false,"given":"Da","family":"Huo","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5094-5331","authenticated-orcid":false,"given":"Zhenzhe","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2571-1979","authenticated-orcid":false,"given":"Xiaoyao","family":"Huang","sequence":"additional","affiliation":[{"name":"Cloud Computing Research Institute, China Telecom, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8423-5522","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"China Telecom Cloud Technology Co. Ltd., Beijing 100033, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0735-6038","authenticated-orcid":false,"given":"Jianfeng","family":"Hu","sequence":"additional","affiliation":[{"name":"China Telecom Cloud Technology Co. Ltd., Beijing 100033, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3174-1019","authenticated-orcid":false,"given":"Zhiyong","family":"Yan","sequence":"additional","affiliation":[{"name":"China Telecom Cloud Technology Co. Ltd., Beijing 100033, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0544-235X","authenticated-orcid":false,"given":"Fan","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3472-1717","authenticated-orcid":false,"given":"Jie","family":"Wu","sequence":"additional","affiliation":[{"name":"Cloud Computing Research Institute, China Telecom, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,12,20]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"2025. Supplementary Material. https:\/\/drive.google.com\/drive\/folders\/1bionk2aooM4q1bHjx9Npqq9AnOBkVI7E?usp=sharing."},{"key":"e_1_3_3_2_3_2","unstructured":"Amazon Web Services. 2024. Amazon Web Services (AWS). https:\/\/aws.amazon.com Accessed: 2024-12-06."},{"key":"e_1_3_3_2_4_2","first-page":"136","volume-title":"ICML","author":"Amos Brandon","year":"2017","unstructured":"Brandon Amos and J.\u00a0Zico Kolter. 2017. OptNet: Differentiable Optimization as a Layer in Neural Networks. In ICML. 136\u2013145."},{"key":"e_1_3_3_2_5_2","unstructured":"Brandon Amos Vladlen Koltun and J.\u00a0Zico Kolter. 2019. The Limited Multi-Label Projection Layer. CoRR abs\/1906.08707 (2019)."},{"key":"e_1_3_3_2_6_2","unstructured":"Lu Bai Weixing Ji Qinyuan Li Xilai Yao Wei Xin and Wanyi Zhu. 2022. DNNAbacus: Toward Accurate Computational Cost Prediction for Deep Neural Networks. CoRR abs\/2205.12095 (2022)."},{"key":"e_1_3_3_2_7_2","first-page":"9508","volume-title":"NeurIPS","author":"Berthet Quentin","year":"2020","unstructured":"Quentin Berthet, Mathieu Blondel, Olivier Teboul, Marco Cuturi, Jean-Philippe Vert, and Francis\u00a0R. Bach. 2020. Learning with Differentiable Pertubed Optimizers. In NeurIPS. 9508\u20139519."},{"key":"e_1_3_3_2_8_2","first-page":"950","volume-title":"ICML","author":"Blondel Mathieu","year":"2020","unstructured":"Mathieu Blondel, Olivier Teboul, Quentin Berthet, and Josip Djolonga. 2020. Fast Differentiable Sorting and Ranking. In ICML. 950\u2013959."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"e_1_3_3_2_10_2","first-page":"5484","volume-title":"NIPS","author":"Donti Priya\u00a0L.","year":"2017","unstructured":"Priya\u00a0L. Donti, J.\u00a0Zico Kolter, and Brandon Amos. 2017. Task-based End-to-end Model Learning in Stochastic Optimization. In NIPS. 5484\u20135494."},{"key":"e_1_3_3_2_11_2","first-page":"10480","volume-title":"NeurIPS","author":"Dudziak Lukasz","year":"2020","unstructured":"Lukasz Dudziak, Thomas Chau, Mohamed\u00a0S. Abdelfattah, Royson Lee, Hyeji Kim, and Nicholas\u00a0D. Lane. 2020. BRP-NAS: Prediction-based NAS using GCNs. In NeurIPS. 10480\u201310490."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Adam\u00a0N. Elmachtoub and Paul Grigas. 2022. Smart \"Predict then Optimize\". Management Science 68 1 (2022) 9\u201326.","DOI":"10.1287\/mnsc.2020.3922"},{"key":"e_1_3_3_2_13_2","unstructured":"Equinix Inc.2024. Equinix: Global Data Center Solutions and Services. Website. https:\/\/www.equinix.com Accessed: 2024-12-06."},{"key":"e_1_3_3_2_14_2","volume-title":"NSDI","author":"Feng Chengquan","year":"2024","unstructured":"Chengquan Feng, Li\u00a0Lyna Zhang, Yuanchi Liu, Jiahang Xu, Chengruidong Zhang, Zhiyuan Wang, Ting Cao, Mao Yang, and Haisheng Tan. 2024. LitePred: Transferable and Scalable Latency Prediction for Hardware-Aware Neural Architecture Search. In NSDI."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP58684.2023.00039"},{"key":"e_1_3_3_2_16_2","unstructured":"Stephen Gould Basura Fernando Anoop Cherian Peter Anderson Rodrigo\u00a0Santa Cruz and Edison Guo. 2016. On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimization. CoRR abs\/1607.05447 (2016)."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Albert\u00a0G. Greenberg James\u00a0R. Hamilton David\u00a0A. Maltz and Parveen Patel. 2009. The cost of a cloud: research problems in data center networks. ACM SIGCOMM computer communication review 39 1 (2009) 68\u201373.","DOI":"10.1145\/1496091.1496103"},{"key":"e_1_3_3_2_18_2","first-page":"485","volume-title":"NSDI","author":"Gu Juncheng","year":"2019","unstructured":"Juncheng Gu, Mosharaf Chowdhury, Kang\u00a0G. Shin, Yibo Zhu, Myeongjae Jeon, Junjie Qian, Hongqiang\u00a0Harry Liu, and Chuanxiong Guo. 2019. Tiresias: A GPU Cluster Manager for Distributed Deep Learning. In NSDI. 485\u2013500."},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2013.6693089"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476223"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575705"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00201"},{"key":"e_1_3_3_2_23_2","first-page":"947","volume-title":"USENIX ATC","author":"Jeon Myeongjae","year":"2019","unstructured":"Myeongjae Jeon, Shivaram Venkataraman, Amar Phanishayee, Junjie Qian, Wencong Xiao, and Fan Yang. 2019. Analysis of Large-Scale Multi-Tenant GPU Clusters for DNN Training Workloads. In USENIX ATC. 947\u2013960."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Tian Li Anit\u00a0Kumar Sahu Ameet Talwalkar and Virginia Smith. 2020. Federated Learning: Challenges Methods and Future Directions. IEEE Signal Process. Mag. 37 3 (2020) 50\u201360.","DOI":"10.1109\/MSP.2020.2975749"},{"key":"e_1_3_3_2_25_2","first-page":"1081","volume-title":"NSDI","author":"Liang Chieh-Jan\u00a0Mike","year":"2023","unstructured":"Chieh-Jan\u00a0Mike Liang, Zilin Fang, Yuqing Xie, Fan Yang, Zhao\u00a0Lucis Li, Li\u00a0Lyna Zhang, Mao Yang, and Lidong Zhou. 2023. On Modular Learning of Distributed Systems for Predicting End-to-End Latency. In NSDI. 1081\u20131095."},{"key":"e_1_3_3_2_26_2","first-page":"153","volume-title":"ICS","author":"Liao Ying-Chiao","year":"2020","unstructured":"Ying-Chiao Liao, Chuan-Chi Wang, Chia-Heng Tu, Ming-Chang Kao, Wen-Yew Liang, and Shih-Hao Hung. 2020. PerfNetRT: Platform-Aware Performance Modeling for Optimized Deep Neural Networks. In ICS. 153\u2013158."},{"key":"e_1_3_3_2_27_2","first-page":"161","volume-title":"USENIX ATC","author":"Lim Gangmuk","year":"2021","unstructured":"Gangmuk Lim, Jeongseob Ahn, Wencong Xiao, Youngjin Kwon, and Myeongjae Jeon. 2021. Zico: Efficient GPU Memory Sharing for Concurrent DNN Training. In USENIX ATC. 161\u2013175."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682877"},{"key":"e_1_3_3_2_29_2","first-page":"14935","volume-title":"ICML","author":"Mandi Jayanta","year":"2022","unstructured":"Jayanta Mandi, V\u00edctor Bucarey, Maxime Mulamba\u00a0Ke Tchomba, and Tias Guns. 2022. Decision-Focused Learning: Through the Lens of Learning to Rank. In ICML. 14935\u201314947."},{"key":"e_1_3_3_2_30_2","volume-title":"NeurIPS","author":"Mandi Jayanta","year":"2020","unstructured":"Jayanta Mandi and Tias Guns. 2020. Interior Point Solving for LP-based prediction+optimisation. In NeurIPS."},{"key":"e_1_3_3_2_31_2","unstructured":"Microsoft Azure. 2024. Microsoft Azure Cloud Services. https:\/\/azure.microsoft.com Accessed: 2024-12-06."},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/390"},{"key":"e_1_3_3_2_33_2","first-page":"14567","volume-title":"NeurIPS","author":"Niepert Mathias","year":"2021","unstructured":"Mathias Niepert, Pasquale Minervini, and Luca Franceschi. 2021. Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions. In NeurIPS. 14567\u201314579."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"e_1_3_3_2_35_2","volume-title":"ICLR","author":"Pogancic Marin\u00a0Vlastelica","year":"2020","unstructured":"Marin\u00a0Vlastelica Pogancic, Anselm Paulus, V\u00edt Musil, Georg Martius, and Michal Rol\u00ednek. 2020. Differentiation of Blackbox Combinatorial Solvers. In ICLR."},{"key":"e_1_3_3_2_36_2","volume-title":"ICLR","author":"Qi Hang","year":"2017","unstructured":"Hang Qi, Evan\u00a0Randall Sparks, and Ameet Talwalkar. 2017. Paleo: A Performance Model for Deep Neural Networks. In ICLR."},{"key":"e_1_3_3_2_37_2","unstructured":"Chuan-Chi Wang Ying-Chiao Liao Ming-Chang Kao Wen-Yew Liang and Shih-Hao Hung. 2020. Toward Accurate Platform-Aware Performance Modeling for Deep Neural Networks. CoRR abs\/2012.00211 (2020)."},{"key":"e_1_3_3_2_38_2","first-page":"945","volume-title":"NSDI","author":"Weng Qizhen","year":"2022","unstructured":"Qizhen Weng, Wencong Xiao, Yinghao Yu, Wei Wang, Cheng Wang, Jian He, Yong Li, Liping Zhang, Wei Lin, and Yu Ding. 2022. MLaaS in the Wild: Workload Analysis and Scheduling in Large-Scale Heterogeneous GPU Clusters. In NSDI. 945\u2013960."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011658"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Gyeongsik Yang Changyong Shin Jeunghwan Lee Yeonho Yoo and Chuck Yoo. 2022. Prediction of the Resource Consumption of Distributed Deep Learning Systems. Proc. ACM Meas. Anal. Comput. Syst. 6 2 (2022) 29:1\u201329:25.","DOI":"10.1145\/3530895"},{"key":"e_1_3_3_2_41_2","volume-title":"HotCloud","author":"Yeung Gingfung","year":"2020","unstructured":"Gingfung Yeung, Damian Borowiec, Adrian Friday, Richard Harper, and Peter Garraghan. 2020. Towards GPU Utilization Prediction for Cloud Deep Learning. In HotCloud."},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"crossref","unstructured":"Gingfung Yeung Damian Borowiec Renyu Yang Adrian Friday Richard Harper and Peter Garraghan. 2022. Horus: Interference-Aware and Prediction-Based Scheduling in Deep Learning Systems. IEEE Trans. Parallel Distributed Syst. 33 1 (2022) 88\u2013100.","DOI":"10.1109\/TPDS.2021.3079202"},{"key":"e_1_3_3_2_43_2","first-page":"503","volume-title":"ATC","author":"Yu Geoffrey\u00a0X.","year":"2021","unstructured":"Geoffrey\u00a0X. Yu, Yubo Gao, Pavel Golikov, and Gennady Pekhimenko. 2021. Habitat: A Runtime-Based Computational Performance Predictor for Deep Neural Network Training. In ATC. 503\u2013521."},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3467882"},{"key":"e_1_3_3_2_45_2","first-page":"11492","volume-title":"ICML","author":"Zhou Dongruo","year":"2020","unstructured":"Dongruo Zhou, Lihong Li, and Quanquan Gu. 2020. Neural Contextual Bandits with UCB-based Exploration. In ICML. 11492\u201311502."}],"event":{"name":"ICPP '25: 54th International Conference on Parallel Processing","location":"San Diego CA USA","acronym":"ICPP '25"},"container-title":["Proceedings of the 54th International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3754598.3754610","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:35:41Z","timestamp":1766219741000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3754598.3754610"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":44,"alternative-id":["10.1145\/3754598.3754610","10.1145\/3754598"],"URL":"https:\/\/doi.org\/10.1145\/3754598.3754610","relation":{},"subject":[],"published":{"date-parts":[[2025,9,8]]},"assertion":[{"value":"2025-12-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}