{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T14:02:56Z","timestamp":1774879376407,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819584130","type":"print"},{"value":"9789819584147","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-8414-7_9","type":"book-chapter","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T13:14:16Z","timestamp":1774876456000},"page":"145-162","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["JAFC: Job-Aware Flow Control for\u00a0Distributed DNN Training"],"prefix":"10.1007","author":[{"given":"Siyan","family":"Pan","sequence":"first","affiliation":[]},{"given":"Xiaobin","family":"Tan","sequence":"additional","affiliation":[]},{"given":"Tiance","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yingying","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Ning","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Feng","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,3,31]]},"reference":[{"key":"9_CR1","unstructured":"Al-Fares, M., Radhakrishnan, S., Raghavan, B., Huang, N., Vahdat, A., et\u00a0al.: Hedera: dynamic flow scheduling for data center networks. In: NSDI, vol.\u00a010, pp. 89\u201392. San Jose, USA (2010)"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Alizadeh, M., et al.: PFABRIC: minimal near-optimal datacenter transport. SIGCOMM Comput. Commun. Rev. 43(4), 435\u2013446 (2013). https:\/\/doi.org\/10.1145\/2534169.2486031","DOI":"10.1145\/2534169.2486031"},{"issue":"4","key":"9_CR3","doi-asserted-by":"publisher","first-page":"1954","DOI":"10.1109\/TNET.2017.2669216","volume":"25","author":"W Bai","year":"2017","unstructured":"Bai, W., Chen, L., Chen, K., Han, D., Tian, C., Wang, H.: PIAS: practical information-agnostic flow scheduling for commodity data centers. IEEE\/ACM Trans. Network. 25(4), 1954\u20131967 (2017). https:\/\/doi.org\/10.1109\/TNET.2017.2669216","journal-title":"IEEE\/ACM Trans. Network."},{"key":"9_CR4","doi-asserted-by":"publisher","unstructured":"Cho, M., Finkler, U., Serrano, M., Kung, D., Hunter, H.: BlueConnect: decomposing all-reduce for deep learning on heterogeneous network hierarchy. IBM J. Res. Dev. 63(6), 1:1\u20131:11 (2019). https:\/\/doi.org\/10.1147\/JRD.2019.2947013","DOI":"10.1147\/JRD.2019.2947013"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Chowdhury, M., Stoica, I.: Efficient COFLOW scheduling without prior knowledge. In: Proceedings of the 2015 ACM Conference on Special Interest Group on Data Communication, pp. 393\u2013406. SIGCOMM 2015, Association for Computing Machinery, New York, NY, USA (2015). https:\/\/doi.org\/10.1145\/2785956.2787480","DOI":"10.1145\/2785956.2787480"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Chowdhury, M., Zhong, Y., Stoica, I.: Efficient COFLOW scheduling with VARYS. In: Proceedings of the 2014 ACM Conference on SIGCOMM, pp. 443\u2013454. SIGCOMM 2014, Association for Computing Machinery, New York, NY, USA (2014). https:\/\/doi.org\/10.1145\/2619239.2626315","DOI":"10.1145\/2619239.2626315"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Hong, C.Y., Caesar, M., Godfrey, P.B.: Finishing flows quickly with preemptive scheduling. SIGCOMM Comput. Commun. Rev. 42(4), 127\u2013138 (2012). https:\/\/doi.org\/10.1145\/2377677.2377710","DOI":"10.1145\/2377677.2377710"},{"key":"9_CR8","unstructured":"Jajoo, A., Hu, Y.C., Lin, X.: Your COFLOW has many flows: Sampling them for fun and speed. In: 2019 USENIX Annual Technical Conference (USENIX ATC 19), pp. 833\u2013848. USENIX Association, Renton, WA (2019). https:\/\/www.usenix.org\/conference\/atc19\/presentation\/jajoo"},{"key":"9_CR9","unstructured":"Jiang, Y., Zhu, Y., Lan, C., Yi, B., Cui, Y., Guo, C.: A unified architecture for accelerating distributed DNN training in heterogeneous GPU\/CPU clusters. In: 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20), pp. 463\u2013479. USENIX Association (2020). https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/jiang"},{"issue":"7553","key":"9_CR10","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"9_CR11","unstructured":"Liang, F., Zhang, Z., Lu, H., Leung, V.C.M., Guo, Y., Hu, X.: Communication-efficient large-scale distributed deep learning: a comprehensive survey (2024). https:\/\/arxiv.org\/abs\/2404.06114"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Montazeri, B., Li, Y., Alizadeh, M., Ousterhout, J.: HOMA: a receiver-driven low-latency transport protocol using network priorities. In: Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication, p. 221\u2013235. SIGCOMM 2018, Association for Computing Machinery, New York, NY, USA (2018). https:\/\/doi.org\/10.1145\/3230543.3230564","DOI":"10.1145\/3230543.3230564"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Mudigere, D., et al.: Software-hardware co-design for fast and scalable training of deep learning recommendation models. In: Proceedings of the 49th Annual International Symposium on Computer Architecture, pp. 993\u20131011. ISCA 2022, Association for Computing Machinery, New York, NY, USA (2022). https:\/\/doi.org\/10.1145\/3470496.3533727","DOI":"10.1145\/3470496.3533727"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Perry, J., Ousterhout, A., Balakrishnan, H., Shah, D., Fugal, H.: FastPass: a centralized \u201czero-queue\u201d datacenter network. In: Proceedings of the 2014 ACM Conference on SIGCOMM, pp. 307\u2013318. SIGCOMM 2014, Association for Computing Machinery, New York, NY, USA (2014). https:\/\/doi.org\/10.1145\/2619239.2626309","DOI":"10.1145\/2619239.2626309"},{"key":"9_CR15","unstructured":"Rajasekaran, S., Ghobadi, M., Akella, A.: CASSINI: network-aware job scheduling in machine learning clusters. In: 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24), pp. 1403\u20131420. USENIX Association, Santa Clara, CA (2024). https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/rajasekaran"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Rajasekaran, S., Narang, S., Zabreyko, A.A., Ghobadi, M.: MLTCP: a distributed technique to approximate centralized flow scheduling for machine learning. In: Proceedings of the 23rd ACM Workshop on Hot Topics in Networks, pp. 167\u2013176. HotNets 2024, Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3696348.3696878","DOI":"10.1145\/3696348.3696878"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Schrage, L.: Letter to the editor\u2014a proof of the optimality of the shortest remaining processing time discipline. Oper. Res. 16(3), 687\u2013690 (1968). https:\/\/doi.org\/10.1287\/opre.16.3.687","DOI":"10.1287\/opre.16.3.687"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Schrage, L.E., Miller, L.W.: The queue m\/g\/1 with the shortest remaining processing time discipline. Oper. Res. 14(4), 670\u2013684 (1966). https:\/\/doi.org\/10.1287\/opre.14.4.670","DOI":"10.1287\/opre.14.4.670"},{"key":"9_CR19","unstructured":"Shazeer, N., Mirhoseini, A., Maziarz, K., Davis, A., Le, Q., Hinton, G., Dean, J.: Outrageously large neural networks: the sparsely-gated mixture-of-experts layer. In: International Conference on Learning Representations (2017). https:\/\/openreview.net\/forum?id=B1ckMDqlg"},{"key":"9_CR20","unstructured":"Wang, W., et al.: TopoOpt: co-optimizing network topology and parallelization strategy for distributed training jobs. In: 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23), pp. 739\u2013767. USENIX Association, Boston, MA (2023). https:\/\/www.usenix.org\/conference\/nsdi23\/presentation\/wang-weiyang"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Liu, Y., Peng, Y., Zhu, Y., Liu, X., Jin, X.: Multi-resource interleaving for deep learning training. In: Proceedings of the ACM SIGCOMM 2022 Conference, pp. 428\u2013440. SIGCOMM 2022, Association for Computing Machinery, New York, NY, USA (2022). https:\/\/doi.org\/10.1145\/3544216.3544224","DOI":"10.1145\/3544216.3544224"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Congestion control for large-scale RDMA deployments. In: Proceedings of the 2015 ACM Conference on Special Interest Group on Data Communication, pp. 523\u2013536. SIGCOMM 2015, Association for Computing Machinery, New York, NY, USA (2015). https:\/\/doi.org\/10.1145\/2785956.2787484","DOI":"10.1145\/2785956.2787484"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-8414-7_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T13:14:22Z","timestamp":1774876462000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-8414-7_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819584130","9789819584147"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-8414-7_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"31 March 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ieee-cybermatics.org\/2025\/ica3pp\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}