{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:58:20Z","timestamp":1777654700834,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62276182"],"award-info":[{"award-number":["No.62276182"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681094","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"2955-2963","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["FedBCGD: Communication-Efficient Accelerated Block Coordinate Gradient Descent for Federated Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4677-800X","authenticated-orcid":false,"given":"Junkang","family":"Liu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1040-352X","authenticated-orcid":false,"given":"Fanhua","family":"Shang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8646-8533","authenticated-orcid":false,"given":"Yuanyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5961-5569","authenticated-orcid":false,"given":"Hongying","family":"Liu","sequence":"additional","affiliation":[{"name":"Medical College, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2259-0687","authenticated-orcid":false,"given":"Yuangang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Southern California, Los Angeles, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4492-3847","authenticated-orcid":false,"given":"YunXiang","family":"Gong","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1045"},{"key":"e_1_3_2_2_2_1","volume-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding. Advances in neural information processing systems 30","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. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3501813"},{"key":"e_1_3_2_2_4_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877--1901."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383455.3422562"},{"key":"e_1_3_2_2_6_1","unstructured":"Ashok Cutkosky and Francesco Orabona. 2019. Momentum-Based Variance Reduction in Non-Convex SGD. In Advances in Neural Information Processing Systems 32 (NeurIPS). 15210--15219."},{"key":"e_1_3_2_2_7_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_8_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00987"},{"key":"e_1_3_2_2_10_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 3556--3564","author":"Gorbunov Eduard","year":"2021","unstructured":"Eduard Gorbunov, Filip Hanzely, and Peter Richt\u00e1rik. 2021. Local SGD: Unified theory and new efficient methods. In International Conference on Artificial Intelligence and Statistics. PMLR, 3556--3564."},{"key":"e_1_3_2_2_11_1","volume-title":"large minibatch sgd: Training imagenet in 1 hour. arXiv preprint arXiv:1706.02677","author":"Goyal Priya","year":"2017","unstructured":"Priya Goyal, Piotr Doll\u00e1r, Ross Girshick, Pieter Noordhuis, Lukasz Wesolowski, Aapo Kyrola, Andrew Tulloch, Yangqing Jia, and Kaiming He. 2017. Accurate, large minibatch sgd: Training imagenet in 1 hour. arXiv preprint arXiv:1706.02677 (2017)."},{"key":"e_1_3_2_2_12_1","unstructured":"Xinran Gu Kaifeng Lyu Longbo Huang and Sanjeev Arora. 2023. Why (and When) does Local SGD Generalize Better than SGD? arXiv preprint arXiv:2303.01215 (2023)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_14_1","volume-title":"Measuring the effects of non-identical data distribution for federated visual classification. arXiv preprint arXiv:1909.06335","author":"Harry Hsu Tzu-Ming","year":"2019","unstructured":"Tzu-Ming Harry Hsu, Hang Qi, and Matthew Brown. 2019. Measuring the effects of non-identical data distribution for federated visual classification. arXiv preprint arXiv:1909.06335 (2019)."},{"key":"e_1_3_2_2_15_1","volume-title":"Accelerating stochastic gradient descent using predictive variance reduction. Advances in neural information processing systems 26","author":"Johnson Rie","year":"2013","unstructured":"Rie Johnson and Tong Zhang. 2013. Accelerating stochastic gradient descent using predictive variance reduction. Advances in neural information processing systems 26 (2013)."},{"key":"e_1_3_2_2_16_1","volume-title":"Mime: Mimicking centralized stochastic algorithms in federated learning. arXiv preprint arXiv:2008.03606","author":"Karimireddy Sai Praneeth","year":"2020","unstructured":"Sai Praneeth Karimireddy, Martin Jaggi, Satyen Kale, Mehryar Mohri, Sashank J Reddi, Sebastian U Stich, and Ananda Theertha Suresh. 2020. Mime: Mimicking centralized stochastic algorithms in federated learning. arXiv preprint arXiv:2008.03606 (2020)."},{"key":"e_1_3_2_2_17_1","volume-title":"International Conference on Machine Learning. PMLR, 5132--5143","author":"Karimireddy Sai Praneeth","year":"2020","unstructured":"Sai Praneeth Karimireddy, Satyen Kale, Mehryar Mohri, Sashank Reddi, Sebastian Stich, and Ananda Theertha Suresh. 2020. Scaffold: Stochastic controlled averaging for federated learning. In International Conference on Machine Learning. PMLR, 5132--5143."},{"key":"e_1_3_2_2_18_1","first-page":"6050","article-title":"Stem: A stochastic two-sided momentum algorithm achieving near-optimal sample and communication complexities for federated learning","volume":"34","author":"Khanduri Prashant","year":"2021","unstructured":"Prashant Khanduri, Pranay Sharma, Haibo Yang, Mingyi Hong, Jia Liu, Ketan Rajawat, and Pramod Varshney. 2021. Stem: A stochastic two-sided momentum algorithm achieving near-optimal sample and communication complexities for federated learning. Advances in Neural Information Processing Systems 34 (2021), 6050--6061.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_19_1","volume-title":"Federated optimization: Distributed machine learning for on-device intelligence.arXiv preprint arXiv:1610.02527","author":"Koneny Jakub","year":"2016","unstructured":"Jakub Koneny, H Brendan McMahan, Daniel Ramage, and Peter Richt\u00e1rik. 2016. Federated optimization: Distributed machine learning for on-device intelligence.arXiv preprint arXiv:1610.02527 (2016)."},{"key":"e_1_3_2_2_20_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_2_21_1","volume-title":"Tiny imagenet visual recognition challenge. CS 231N 7, 7","author":"Le Ya","year":"2015","unstructured":"Ya Le and Xuan Yang. 2015. Tiny imagenet visual recognition challenge. CS 231N 7, 7 (2015), 3."},{"key":"e_1_3_2_2_22_1","unstructured":"Yann LeCun et al. 2015. LeNet-5 convolutional neural networks. URL: http:\/\/yann. lecun. com\/exdb\/lenet 20 5 (2015) 14."},{"key":"e_1_3_2_2_23_1","unstructured":"B Li and et al. [n. d.]. On the effectiveness of partial variance reduction in federated learning with heterogeneous data. CVPR ([n. d.])."},{"key":"e_1_3_2_2_24_1","volume-title":"Vertical federated learning. arXiv preprint arXiv:2211.12814","author":"Liu Yang","year":"2022","unstructured":"Yang Liu, Yan Kang, Tianyuan Zou, Yanhong Pu, Yuanqin He, Xiaozhou Ye, Ye Ouyang, Ya-Qin Zhang, and Qiang Yang. 2022. Vertical federated learning. arXiv preprint arXiv:2211.12814 (2022)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3198176"},{"key":"e_1_3_2_2_26_1","first-page":"5972","article-title":"No fear of heterogeneity: Classifier calibration for federated learning with non-iid data","volume":"34","author":"Luo Mi","year":"2021","unstructured":"Mi Luo, Fei Chen, Dapeng Hu, Yifan Zhang, Jian Liang, and Jiashi Feng. 2021. No fear of heterogeneity: Classifier calibration for federated learning with non-iid data. Advances in Neural Information Processing Systems 34 (2021), 5972--5984.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/3122009.3176835"},{"key":"e_1_3_2_2_28_1","unstructured":"Brendan McMahan Eider Moore Daniel Ramage Seth Hampson and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics. PMLR 1273--1282."},{"key":"e_1_3_2_2_29_1","first-page":"14606","article-title":"Linear convergence in federated learning: Tackling client heterogeneity and sparse gradients","volume":"34","author":"Mitra Aritra","year":"2021","unstructured":"Aritra Mitra, Rayana Jaafar, George J Pappas, and Hamed Hassani. 2021. Linear convergence in federated learning: Tackling client heterogeneity and sparse gradients. Advances in Neural Information Processing Systems 34 (2021), 14606-- 14619.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_30_1","volume-title":"Bias-variance reduced local sgd for less heterogeneous federated learning. arXiv preprint arXiv:2102.03198","author":"Murata Tomoya","year":"2021","unstructured":"Tomoya Murata and Taiji Suzuki. 2021. Bias-variance reduced local sgd for less heterogeneous federated learning. arXiv preprint arXiv:2102.03198 (2021)."},{"key":"e_1_3_2_2_31_1","first-page":"13316","article-title":"Towards optimal communication complexity in distributed non-convex optimization","volume":"35","author":"Patel Kumar Kshitij","year":"2022","unstructured":"Kumar Kshitij Patel, Lingxiao Wang, Blake E Woodworth, Brian Bullins, and Nati Srebro. 2022. Towards optimal communication complexity in distributed non-convex optimization. Advances in Neural Information Processing Systems 35 (2022), 13316--13328.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_32_1","volume-title":"Adaptive feder-ated optimization. arXiv preprint arXiv:2003.00295","author":"Reddi Sashank","year":"2020","unstructured":"Sashank Reddi, Zachary Charles, Manzil Zaheer, Zachary Garrett, Keith Rush, Jakub Koneny, Sanjiv Kumar, and H Brendan McMahan. 2020. Adaptive feder-ated optimization. arXiv preprint arXiv:2003.00295 (2020)."},{"key":"e_1_3_2_2_33_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR","author":"Reisizadeh Amirhossein","year":"2020","unstructured":"Amirhossein Reisizadeh, Aryan Mokhtari, Hamed Hassani, Ali Jadbabaie, and Ramtin Pedarsani. 2020. Fedpaq: A communication-efficient federated learning method with periodic averaging and quantization. In International Conference on Artificial Intelligence and Statistics. PMLR, 2021--2031."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.3007028"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"crossref","unstructured":"Nicola Rieke Jonny Hancox Wenqi Li Fausto Milletari Holger R Roth Shadi Albarqouni Spyridon Bakas Mathieu N Galtier Bennett A Landman Klaus MaierHein et al. 2020. The future of digital health with federated learning. NPJ digital medicine 3 1 (2020) 119.","DOI":"10.1038\/s41746-020-00323-1"},{"key":"e_1_3_2_2_36_1","volume-title":"Robust and communication-efficient federated learning from non-iid data","author":"Sattler Felix","year":"2019","unstructured":"Felix Sattler, Simon Wiedemann, Klaus-Robert M\u00fcller, and Wojciech Samek. 2019. Robust and communication-efficient federated learning from non-iid data. IEEE transactions on neural networks and learning systems 31, 9 (2019), 3400--3413."},{"key":"e_1_3_2_2_37_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_2_38_1","volume-title":"Coordinate descent algorithms. Mathematical programming 151, 1","author":"Wright Stephen J","year":"2015","unstructured":"Stephen J Wright. 2015. Coordinate descent algorithms. Mathematical programming 151, 1 (2015), 3--34."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3339474"},{"key":"e_1_3_2_2_40_1","volume-title":"International conference on machine learning. PMLR, 7313--7323","author":"Zeng Jinshan","year":"2019","unstructured":"Jinshan Zeng, Tim Tsz-Kit Lau, Shaobo Lin, and Yuan Yao. 2019. Global convergence of block coordinate descent in deep learning. In International conference on machine learning. PMLR, 7313--7323."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681094","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:52Z","timestamp":1750294672000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681094"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":40,"alternative-id":["10.1145\/3664647.3681094","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681094","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}