{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:12:04Z","timestamp":1768255924621,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"King Abdullah University of Science and Technology Research Funding (KRF)","award":["ORA-2021-CRG9-4382"],"award-info":[{"award-number":["ORA-2021-CRG9-4382"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,8]]},"DOI":"10.1145\/3630048.3630184","type":"proceedings-article","created":{"date-parts":[[2023,11,28]],"date-time":"2023-11-28T19:42:35Z","timestamp":1701200555000},"page":"35-48","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Kimad: Adaptive Gradient Compression with Bandwidth Awareness"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8117-9422","authenticated-orcid":false,"given":"Jihao","family":"Xin","sequence":"first","affiliation":[{"name":"KAUST, Thuwal, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6210-378X","authenticated-orcid":false,"given":"Ivan","family":"Ilin","sequence":"additional","affiliation":[{"name":"KAUST, Thuwal, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7747-4667","authenticated-orcid":false,"given":"Shunkang","family":"Zhang","sequence":"additional","affiliation":[{"name":"HKUST, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5051-4283","authenticated-orcid":false,"given":"Marco","family":"Canini","sequence":"additional","affiliation":[{"name":"KAUST, Thuwal, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4380-5848","authenticated-orcid":false,"given":"Peter","family":"Richt\u00e1rik","sequence":"additional","affiliation":[{"name":"KAUST, Thuwal, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,12,5]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Ahmed M Abdelmoniem and Marco Canini. 2021. DC2: Delay-aware compression control for distributed machine learning. In INFOCOM.","DOI":"10.1109\/INFOCOM42981.2021.9488810"},{"key":"e_1_3_2_1_2_1","volume-title":"Accordion: Adaptive Gradient Communication via Critical Learning Regime Identification. In MLSys.","author":"Agarwal Saurabh","year":"2021","unstructured":"Saurabh Agarwal, Hongyi Wang, Kangwook Lee, Shivaram Venkataraman, and Dimitris Papailiopoulos. 2021. Accordion: Adaptive Gradient Communication via Critical Learning Regime Identification. In MLSys."},{"key":"e_1_3_2_1_3_1","unstructured":"Mohammadreza Alimohammadi Ilia Markov Elias Frantar and Dan Alistarh. 2022. L-GreCo: An Efficient and General Framework for Layerwise-Adaptive Gradient Compression. arXiv:2210.17357 [cs.LG]"},{"key":"e_1_3_2_1_4_1","volume-title":"QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding. In NeurIPS.","author":"Alistarh Dan","year":"2017","unstructured":"Dan Alistarh, Demjan Grubic, Jerry Li, Ryota Tomioka, and Milan Vojnovic. 2017. QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding. In NeurIPS."},{"key":"e_1_3_2_1_5_1","unstructured":"Dan Alistarh Torsten Hoefler Mikael Johansson Sarit Khirirat Nikola Konstantinov and C\u00e9dric Renggli. 2018. The Convergence of Sparsified Gradient Methods. In NeurIPS."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Manu Anand. 2012. Cloud monitor: Monitoring applications in cloud. In CCEM.","DOI":"10.1109\/CCEM.2012.6354603"},{"key":"e_1_3_2_1_7_1","unstructured":"Eddy Caron Luis Rodero-Merino Fr\u00e9d\u00e9ric Desprez and Adrian Muresan. 2012. Auto-scaling load balancing and monitoring in commercial and open-source clouds. Ph.D. Dissertation. INRIA."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Changan Chen Frederick Tung Naveen Vedula and Greg Mori. 2018. Constraint-aware deep neural network compression. In ECCV.","DOI":"10.1007\/978-3-030-01237-3_25"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2023.3256796"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3061394"},{"key":"e_1_3_2_1_11_1","unstructured":"Ilyas Fatkhullin Igor Sokolov Eduard Gorbunov Zhize Li and Peter Richt\u00e1rik. 2021. EF21 with Bells & Whistles: Practical Algorithmic Extensions of Modern Error Feedback. arXiv:2110.03294 [cs.LG]"},{"key":"e_1_3_2_1_12_1","volume-title":"Marco Canini, and Amedeo Sapio.","author":"Fei Jiawei","year":"2021","unstructured":"Jiawei Fei, Chen-Yu Ho, Atal Narayan Sahu, Marco Canini, and Amedeo Sapio. 2021. Efficient Sparse Collective Communication and its application to Accelerate Distributed Deep Learning. In SIGCOMM."},{"key":"e_1_3_2_1_13_1","volume-title":"Marco Canini, and Peter Richt\u00e1rik.","author":"Horv\u00e1th Samuel","year":"2022","unstructured":"Samuel Horv\u00e1th, Chen-Yu Ho, Ludovit Horvath, Atal Narayan Sahu, Marco Canini, and Peter Richt\u00e1rik. 2022. Natural Compression for Distributed Deep Learning. In MSML."},{"key":"e_1_3_2_1_14_1","volume-title":"First Analysis of Local GD on Heterogeneous Data. In NeurIPS Workshop on Federated Learning for Data Privacy and Confidentiality.","author":"Khaled Ahmed","year":"2019","unstructured":"Ahmed Khaled, Konstantin Mishchenko, and Peter Richt\u00e1rik. 2019. First Analysis of Local GD on Heterogeneous Data. In NeurIPS Workshop on Federated Learning for Data Privacy and Confidentiality."},{"key":"e_1_3_2_1_15_1","unstructured":"Ahmed Khaled Konstantin Mishchenko and Peter Richt\u00e1rik. 2020. Tighter Theory for Local SGD on Identical and Heterogeneous Data. In AISTATS."},{"key":"e_1_3_2_1_16_1","volume-title":"Joo Seong Jeong, and Byung-Gon Chun","author":"Kim Soojeong","year":"2019","unstructured":"Soojeong Kim, Gyeong-In Yu, Hojin Park, Sungwoo Cho, Eunji Jeong, Hyeonmin Ha, Sanha Lee, Joo Seong Jeong, and Byung-Gon Chun. 2019. Parallax: Sparsity-aware Data Parallel Training of Deep Neural Networks. In EuroSys."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.3389\/fams.2018.00062"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Jinho Lee Inseok Hwang Soham Shah and Minsik Cho. 2020. FlexReduce: Flexible All-reduce for Distributed Deep Learning on Asymmetric Network Topology. In DAC.","DOI":"10.1109\/DAC18072.2020.9218538"},{"key":"e_1_3_2_1_19_1","unstructured":"Xiang Li Kaixuan Huang Wenhao Yang Shusen Wang and Zhihua Zhang. 2020. On the Convergence of FedAvg on Non-IID Data. In ICLR."},{"key":"e_1_3_2_1_20_1","unstructured":"Liang Luo Peter West Arvind Krishnamurthy Luis Ceze and Jacob Nelson. 2020. PLink: Discovering And Exploiting Datacenter Network Locality For Efficient Cloud-based Distributed Training."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528535.3565248"},{"key":"e_1_3_2_1_22_1","unstructured":"Konstantin Mishchenko Eduard Gorbunov Martin Tak\u00e1\u010d and Peter Richt\u00e1rik. 2019. Distributed Learning with Compressed Gradient Differences. arXiv:1901.09269 [cs.LG]"},{"key":"e_1_3_2_1_23_1","unstructured":"Peter Richt\u00e1rik Igor Sokolov and Ilyas Fatkhullin. 2021. EF21: A New Simpler Theoretically Better and Practically Faster Error Feedback. In NeurIPS."},{"key":"e_1_3_2_1_24_1","unstructured":"Peter Richt\u00e1rik Igor Sokolov Ilyas Fatkhullin Elnur Gasanov Zhize Li and Eduard Gorbunov. 2022. 3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation. arXiv:2202.00998 [cs.LG]"},{"key":"e_1_3_2_1_25_1","unstructured":"Anit Kumar Sahu Tian Li Maziar Sanjabi Manzil Zaheer Ameet Talwalkar and Virginia Smith. 2020. Federated Optimization in Heterogeneous Networks. In MLSys."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Frank Seide Hao Fu Jasha Droppo Gang Li and Dong Yu. 2014. 1-Bit Stochastic Gradient Descent and Application to Data-Parallel Distributed Training of Speech DNNs. In Interspeech.","DOI":"10.21437\/Interspeech.2014-274"},{"key":"e_1_3_2_1_27_1","unstructured":"Alan Shieh Srikanth Kandula Albert Greenberg Changhoon Kim and Bikas Saha. 2011. Sharing the Data Center Network. In NSDI."},{"key":"e_1_3_2_1_28_1","unstructured":"Sebastian U Stich Jean-Baptiste Cordonnier and Martin Jaggi. 2018. Sparsified SGD with Memory. In NeurIPS."},{"key":"e_1_3_2_1_29_1","unstructured":"Ananda Theertha Suresh Felix X. Yu Sanjiv Kumar and H. Brendan McMahan. 2017. Distributed Mean Estimation with Limited Communication. In ICML."},{"key":"e_1_3_2_1_30_1","volume-title":"Sai Praneeth Karimireddy, and Martin Jaggi","author":"Vogels Thijs","year":"2019","unstructured":"Thijs Vogels, Sai Praneeth Karimireddy, and Martin Jaggi. 2019. PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization. In NeurIPS."},{"key":"e_1_3_2_1_31_1","volume-title":"Atomo: Communication-efficient learning via atomic sparsification. In NeurIPS.","author":"Wang Hongyi","year":"2018","unstructured":"Hongyi Wang, Scott Sievert, Shengchao Liu, Zachary Charles, Dimitris Papailiopoulos, and Stephen Wright. 2018. Atomo: Communication-efficient learning via atomic sparsification. In NeurIPS."},{"key":"e_1_3_2_1_32_1","volume-title":"Christopher Re, and Ce Zhang.","author":"Wang Jue","year":"2023","unstructured":"Jue Wang, Yucheng Lu, Binhang Yuan, Beidi Chen, Percy Liang, Christopher De Sa, Christopher Re, and Ce Zhang. 2023. CocktailSGD: Fine-tuning Foundation Models over 500Mbps Networks. In ICML."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904348"},{"key":"e_1_3_2_1_34_1","volume-title":"Egeria: Efficient DNN Training with Knowledge-Guided Layer Freezing. In EuroSys.","author":"Wang Yiding","year":"2023","unstructured":"Yiding Wang, Decang Sun, Kai Chen, Fan Lai, and Mosharaf Chowdhury. 2023. Egeria: Efficient DNN Training with Knowledge-Guided Layer Freezing. In EuroSys."},{"key":"e_1_3_2_1_35_1","unstructured":"Wei Wen Cong Xu Feng Yan Chunpeng Wu Yandan Wang Yiran Chen and Hai Li. 2017. TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning. In NeurIPS."},{"key":"e_1_3_2_1_36_1","volume-title":"Konstantinos Karatsenidis, Marco Canini, and Panos Kalnis.","author":"Xu Hang","year":"2021","unstructured":"Hang Xu, Chen-Yu Ho, Ahmed M. Abdelmoniem, Aritra Dutta, El Houcine Bergou, Konstantinos Karatsenidis, Marco Canini, and Panos Kalnis. 2021. GRACE: A Compressed Communication Framework for Distributed Machine Learning. In ICDCS."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3113346"}],"event":{"name":"CoNEXT 2023: The 19th International Conference on emerging Networking EXperiments and Technologies","location":"Paris France","acronym":"CoNEXT 2023","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the 4th International Workshop on Distributed Machine Learning"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3630048.3630184","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3630048.3630184","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T20:14:58Z","timestamp":1755980098000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3630048.3630184"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,5]]},"references-count":37,"alternative-id":["10.1145\/3630048.3630184","10.1145\/3630048"],"URL":"https:\/\/doi.org\/10.1145\/3630048.3630184","relation":{},"subject":[],"published":{"date-parts":[[2023,12,5]]},"assertion":[{"value":"2023-12-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}