{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:22:57Z","timestamp":1784132577637,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1145\/3718958.3750499","type":"proceedings-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T16:54:11Z","timestamp":1756313651000},"page":"645-662","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["SyCCL: Exploiting Symmetry for Efficient Collective Communication Scheduling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5468-7366","authenticated-orcid":false,"given":"Jiamin","family":"Cao","sequence":"first","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5661-6617","authenticated-orcid":false,"given":"Shangfeng","family":"Shi","sequence":"additional","affiliation":[{"name":"Tsinghua University and Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3548-2030","authenticated-orcid":false,"given":"Jiaqi","family":"Gao","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Seattle, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4206-0384","authenticated-orcid":false,"given":"Weisen","family":"Liu","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6868-1220","authenticated-orcid":false,"given":"Yifan","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University and Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7436-171X","authenticated-orcid":false,"given":"Yichi","family":"Xu","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1907-1882","authenticated-orcid":false,"given":"Zhilong","family":"Zheng","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0726-3933","authenticated-orcid":false,"given":"Yu","family":"Guan","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9882-9279","authenticated-orcid":false,"given":"Kun","family":"Qian","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4919-1130","authenticated-orcid":false,"given":"Ying","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4847-4585","authenticated-orcid":false,"given":"Mingwei","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9602-8417","authenticated-orcid":false,"given":"Tianshu","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2992-8852","authenticated-orcid":false,"given":"Ning","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0939-8943","authenticated-orcid":false,"given":"Jianbo","family":"Dong","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1213-0554","authenticated-orcid":false,"given":"Binzhang","family":"Fu","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7272-8143","authenticated-orcid":false,"given":"Dennis","family":"Cai","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Sunnyvale, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4352-7497","authenticated-orcid":false,"given":"Ennan","family":"Zhai","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Double binary tree 2019. https:\/\/developer.nvidia.com\/blog\/massively-scale-deep-learning-training-nccl-2-4\/."},{"key":"e_1_3_2_1_2_1","unstructured":"Multi-rail topology 2022. https:\/\/developer.nvidia.com\/blog\/doubling-all2all-performance-with-nvidia-collective-communication-library-2-12\/."},{"key":"e_1_3_2_1_3_1","unstructured":"Astra-sim 2.0 2024. https:\/\/github.com\/astra-sim\/astra-sim."},{"key":"e_1_3_2_1_4_1","unstructured":"Bus bandwith computation 2024. https:\/\/github.com\/NVIDIA\/nccl-tests\/blob\/master\/doc\/PERFORMANCE.md."},{"key":"e_1_3_2_1_5_1","unstructured":"cann-hccl 2024. https:\/\/gitee.com\/ascend\/cann-hccl."},{"key":"e_1_3_2_1_6_1","unstructured":"Clos network 2024. https:\/\/en.wikipedia.org\/wiki\/Clos_network."},{"key":"e_1_3_2_1_7_1","unstructured":"Deepspeed 2024. https:\/\/github.com\/microsoft\/DeepSpeed."},{"key":"e_1_3_2_1_8_1","unstructured":"Gloo 2024. https:\/\/github.com\/facebookincubator\/gloo."},{"key":"e_1_3_2_1_9_1","unstructured":"Megatron-lm 2024. https:\/\/github.com\/NVIDIA\/Megatron-LM\/."},{"key":"e_1_3_2_1_10_1","unstructured":"Msccl-executor-nccl 2024. https:\/\/github.com\/Azure\/msccl-executor-nccl."},{"key":"e_1_3_2_1_11_1","unstructured":"Nccl 2024. https:\/\/github.com\/NVIDIA\/nccl."},{"key":"e_1_3_2_1_12_1","unstructured":"Nvidia gb200 nvl72 2024. https:\/\/www.nvidia.com\/en-us\/data-center\/gb200-nvl72\/."},{"key":"e_1_3_2_1_13_1","unstructured":"Nvlink and nvlink switch 2024. https:\/\/www.nvidia.com\/en-us\/data-center\/nvlink\/."},{"key":"e_1_3_2_1_14_1","unstructured":"rccl 2024. https:\/\/github.com\/ROCm\/rccl."},{"key":"e_1_3_2_1_15_1","unstructured":"vllm 2024. https:\/\/github.com\/vllm-project\/vllm."},{"key":"e_1_3_2_1_16_1","volume-title":"Language models are few-shot learners. CoRR, abs\/2005.14165","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. Language models are few-shot learners. CoRR, abs\/2005.14165, 2020."},{"key":"e_1_3_2_1_17_1","first-page":"75","volume-title":"PPoPP '21: 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, Virtual Event, Republic of Korea","author":"Cai Zixian","year":"2021","unstructured":"Zixian Cai, Zhengyang Liu, Saeed Maleki, Madanlal Musuvathi, Todd Mytkowicz, Jacob Nelson, and Olli Saarikivi. Synthesizing optimal collective algorithms. In Jaejin Lee and Erez Petrank, editors, PPoPP '21: 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, Virtual Event, Republic of Korea, February 27- March 3, 2021, pages 62\u201375. ACM, 2021."},{"key":"e_1_3_2_1_18_1","first-page":"15","volume-title":"Proceedings of the ACM SIGCOMM 2024 Conference, ACM SIGCOMM 2024","author":"Cao Jiamin","year":"2024","unstructured":"Jiamin Cao, Yu Guan, Kun Qian, Jiaqi Gao, Wencong Xiao, Jianbo Dong, Binzhang Fu, Dennis Cai, and Ennan Zhai. Crux: Gpu-efficient communication scheduling for deep learning training. In Proceedings of the ACM SIGCOMM 2024 Conference, ACM SIGCOMM 2024, Sydney, NSW, Australia, August 4\u20138, 2024, pages 1\u201315. ACM, 2024."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. BERT: pre-training of deep bidirectional transformers for language understanding. In Jill Burstein, Christy Doran, and Thamar Solorio, editors, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2\u20137, 2019, Volume 1 (Long and Short Papers), pages 4171\u20134186. Association for Computational Linguistics, 2019."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. BERT: pre-training of deep bidirectional transformers for language understanding. In Jill Burstein, Christy Doran, and Thamar Solorio, editors, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2\u20137, 2019, Volume 1 (Long and Short Papers), pages 4171\u20134186. Association for Computational Linguistics, 2019."},{"key":"e_1_3_2_1_21_1","first-page":"15438","volume-title":"Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI","author":"Ding Yifan","year":"2021","unstructured":"Yifan Ding, Nicholas Botzer, and Tim Weninger. Hetseq: Distributed GPU training on heterogeneous infrastructure. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2\u20139, 2021, pages 15432\u201315438. AAAI Press, 2021."},{"key":"e_1_3_2_1_22_1","volume-title":"Boosting large-scale parallel training efficiency with C4: A communication-driven approach. CoRR, abs\/2406.04594","author":"Dong Jianbo","year":"2024","unstructured":"Jianbo Dong, Bin Luo, Jun Zhang, Pengcheng Zhang, Fei Feng, Yikai Zhu, Ang Liu, Zian Chen, Yi Shi, Hairong Jiao, Gang Lu, Yu Guan, Ennan Zhai, Wencong Xiao, Hanyu Zhao, Man Yuan, Siran Yang, Xiang Li, Jiamang Wang, Rui Men, Jianwei Zhang, Huang Zhong, Dennis Cai, Yuan Xie, and Binzhang Fu. Boosting large-scale parallel training efficiency with C4: A communication-driven approach. CoRR, abs\/2406.04594, 2024."},{"key":"e_1_3_2_1_23_1","volume-title":"Using MPI - Portable Parallel Programming with the Message-Passing Interface","author":"Gropp William D.","year":"2014","unstructured":"William D. Gropp, Ewing L. Lusk, and Anthony Skjellum. Using MPI - Portable Parallel Programming with the Message-Passing Interface, 3rd Edition. Scientific and engineering computation. MIT Press, 2014.","edition":"3"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(06)80021-9"},{"key":"e_1_3_2_1_25_1","first-page":"112","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","author":"Huang Yanping","year":"2019","unstructured":"Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Dehao Chen, Mia Xu Chen, HyoukJoong Lee, Jiquan Ngiam, Quoc V. Le, Yonghui Wu, and Zhifeng Chen. Gpipe: Efficient training of giant neural networks using pipeline parallelism. In Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alch\u00e9-Buc, Emily B. Fox, and Roman Garnett, editors, Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8\u201314, 2019, Vancouver, BC, Canada, pages 103\u2013112, 2019."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"e_1_3_2_1_27_1","first-page":"498","volume-title":"Proceedings of the ACM SIGCOMM 2023 Conference, ACM SIGCOMM 2023","author":"Liu Juncai","year":"2023","unstructured":"Juncai Liu, Jessie Hui Wang, and Yimin Jiang. Janus: A unified distributed training framework for sparse mixture-of-experts models. In Henning Schulzrinne, Vishal Misra, Eddie Kohler, and David A. Maltz, editors, Proceedings of the ACM SIGCOMM 2023 Conference, ACM SIGCOMM 2023, New York, NY, USA, 10\u201314 September 2023, pages 486\u2013498. ACM, 2023."},{"key":"e_1_3_2_1_28_1","first-page":"37","volume-title":"Proceedings of the ACM SIGCOMM 2024 Conference, ACM SIGCOMM 2024","author":"Liu Xuting","year":"2024","unstructured":"Xuting Liu, Behnaz Arzani, Siva Kesava Reddy Kakarla, Liangyu Zhao, Vincent Liu, Miguel Castro, Srikanth Kandula, and Luke Marshall. Rethinking machine learning collective communication as a multi-commodity flow problem. In Proceedings of the ACM SIGCOMM 2024 Conference, ACM SIGCOMM 2024, Sydney, NSW, Australia, August 4\u20138, 2024, pages 16\u201337. ACM, 2024."},{"key":"e_1_3_2_1_29_1","first-page":"824","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2023","author":"Mahajan Kshiteej","year":"2023","unstructured":"Kshiteej Mahajan, Ching-Hsiang Chu, Srinivas Sridharan, and Aditya Akella. Better together: Jointly optimizing ML collective scheduling and execution planning using SYNDICATE. In Mahesh Balakrishnan and Manya Ghobadi, editors, 20th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2023, Boston, MA, April 17\u201319, 2023, pages 809\u2013824. USENIX Association, 2023."},{"key":"e_1_3_2_1_30_1","first-page":"706","volume-title":"Proceedings of the ACM SIGCOMM 2024 Conference, ACM SIGCOMM 2024","author":"Qian Kun","year":"2024","unstructured":"Kun Qian, Yongqing Xi, Jiamin Cao, Jiaqi Gao, Yichi Xu, Yu Guan, Binzhang Fu, Xuemei Shi, Fangbo Zhu, Rui Miao, Chao Wang, Peng Wang, Pengcheng Zhang, Xianlong Zeng, Eddie Ruan, Zhiping Yao, Ennan Zhai, and Dennis Cai. Alibaba HPN: A data center network for large language model training. In Proceedings of the ACM SIGCOMM 2024 Conference, ACM SIGCOMM 2024, Sydney, NSW, Australia, August 4\u20138, 2024, pages 691\u2013706. ACM, 2024."},{"key":"e_1_3_2_1_31_1","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation, NSDI 2024","author":"Rajasekaran Sudarsanan","year":"2024","unstructured":"Sudarsanan Rajasekaran, Manya Ghobadi, and Aditya Akella. CASSINI: network-aware job scheduling in machine learning clusters. In Laurent Vanbever and Irene Zhang, editors, 21st USENIX Symposium on Networked Systems Design and Implementation, NSDI 2024, Santa Clara, CA, April 15\u201317, 2024. USENIX Association, 2024."},{"key":"e_1_3_2_1_32_1","first-page":"596","volume-title":"ISCA '22: The 49th Annual International Symposium on Computer Architecture","author":"Rashidi Saeed","year":"2022","unstructured":"Saeed Rashidi, William Won, Sudarshan Srinivasan, Srinivas Sridharan, and Tushar Krishna. Themis: a network bandwidth-aware collective scheduling policy for distributed training of DL models. In Valentina Salapura, Mohamed Zahran, Fred Chong, and Lingjia Tang, editors, ISCA '22: The 49th Annual International Symposium on Computer Architecture, New York, New York, USA, June 18 - 22, 2022, pages 581\u2013596. ACM, 2022."},{"key":"e_1_3_2_1_33_1","first-page":"612","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2023","author":"Shah Aashaka","year":"2023","unstructured":"Aashaka Shah, Vijay Chidambaram, Meghan Cowan, Saeed Maleki, Madan Musuvathi, Todd Mytkowicz, Jacob Nelson, and Olli Saarikivi. TACCL: guiding collective algorithm synthesis using communication sketches. In Mahesh Balakrishnan and Manya Ghobadi, editors, 20th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2023, Boston, MA, April 17\u201319, 2023, pages 593\u2013612. USENIX Association, 2023."},{"key":"e_1_3_2_1_34_1","volume-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings. OpenReview.net","author":"Shazeer Noam","year":"2017","unstructured":"Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc V. Le, Geoffrey E. Hinton, and Jeff Dean. Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings. OpenReview.net, 2017."},{"key":"e_1_3_2_1_35_1","volume-title":"Llama: Open and efficient foundation language models. CoRR, abs\/2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, Aur\u00e9lien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. Llama: Open and efficient foundation language models. CoRR, abs\/2302.13971, 2023."},{"key":"e_1_3_2_1_36_1","first-page":"578","volume-title":"Proceedings of the 2024 USENIX Annual Technical Conference, USENIX ATC 2024","author":"Um Taegeon","year":"2024","unstructured":"Taegeon Um, Byungsoo Oh, Minyoung Kang, Woo-Yeon Lee, Goeun Kim, Dongseob Kim, Youngtaek Kim, Mohd Muzzammil, and Myeongjae Jeon. Metis: Fast automatic distributed training on heterogeneous gpus. In Saurabh Bagchi and Yiying Zhang, editors, Proceedings of the 2024 USENIX Annual Technical Conference, USENIX ATC 2024, Santa Clara, CA, USA, July 10\u201312, 2024, pages 563\u2013578. USENIX Association, 2024."},{"key":"e_1_3_2_1_37_1","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett, editors, Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4\u20139, 2017, Long Beach, CA, USA, pages 5998\u20136008, 2017."},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the Third Conference on Machine Learning and Systems, MLSys 2020","author":"Wang Guanhua","year":"2020","unstructured":"Guanhua Wang, Shivaram Venkataraman, Amar Phanishayee, Jorgen Thelin, Nikhil R. Devanur, and Ion Stoica. Blink: Fast and generic collectives for distributed ML. In Inderjit S. Dhillon, Dimitris S. Papailiopoulos, and Vivienne Sze, editors, Proceedings of the Third Conference on Machine Learning and Systems, MLSys 2020, Austin, TX, USA, March 2\u20134, 2020. mlsys.org, 2020."},{"key":"e_1_3_2_1_39_1","first-page":"767","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2023","author":"Wang Weiyang","year":"2023","unstructured":"Weiyang Wang, Moein Khazraee, Zhizhen Zhong, Manya Ghobadi, Zhihao Jia, Dheevatsa Mudigere, Ying Zhang, and Anthony Kewitsch. Topoopt: Co-optimizing network topology and parallelization strategy for distributed training jobs. In Mahesh Balakrishnan and Manya Ghobadi, editors, 20th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2023, Boston, MA, April 17\u201319, 2023, pages 739\u2013767. USENIX Association, 2023."},{"key":"e_1_3_2_1_40_1","first-page":"683","volume-title":"22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25)","author":"Xu Guanbin","year":"2025","unstructured":"Guanbin Xu, Zhihao Le, Yinhe Chen, Zhiqi Lin, Zewen Jin, Youshan Miao, and Cheng Li. {AutoCCL}: Automated collective communication tuning for accelerating distributed and parallel {DNN} training. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25), pages 667\u2013683, 2025."},{"key":"e_1_3_2_1_41_1","volume-title":"Deep learning-based multimodal emotion recognition from audio, visual, and text modalities: A systematic review of recent advancements and future prospects. Expert Syst. Appl., 237(Part C):121692","author":"Zhang Shiqing","year":"2024","unstructured":"Shiqing Zhang, Yijiao Yang, Chen Chen, Xingnan Zhang, Qingming Leng, and Xiaoming Zhao. Deep learning-based multimodal emotion recognition from audio, visual, and text modalities: A systematic review of recent advancements and future prospects. Expert Syst. Appl., 237(Part C):121692, 2024."},{"key":"e_1_3_2_1_42_1","volume-title":"Optimal direct-connect topologies for collective communications. CoRR, abs\/2202.03356","author":"Zhao Liangyu","year":"2022","unstructured":"Liangyu Zhao, Siddharth Pal, Tapan Chugh, Weiyang Wang, Prithwish Basu, Joud Khoury, and Arvind Krishnamurthy. Optimal direct-connect topologies for collective communications. CoRR, abs\/2202.03356, 2022."}],"event":{"name":"SIGCOMM '25: ACM SIGCOMM 2025 Conference","location":"S\u00e3o Francisco Convent Coimbra Portugal","acronym":"SIGCOMM '25","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the ACM SIGCOMM 2025 Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3718958.3750499","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T17:02:03Z","timestamp":1756314123000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3718958.3750499"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,27]]},"references-count":42,"alternative-id":["10.1145\/3718958.3750499","10.1145\/3718958"],"URL":"https:\/\/doi.org\/10.1145\/3718958.3750499","relation":{},"subject":[],"published":{"date-parts":[[2025,8,27]]},"assertion":[{"value":"2025-08-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}