{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:15:53Z","timestamp":1785543353722,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,7,10]],"date-time":"2022-07-10T00:00:00Z","timestamp":1657411200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Hong Kong RGC Research Impact Fund (RIF)","award":["R5060-19"],"award-info":[{"award-number":["R5060-19"]}]},{"name":"General Research Fund (GRF)","award":["152221\/19E, 152203\/20E, 152244\/21E"],"award-info":[{"award-number":["152221\/19E, 152203\/20E, 152244\/21E"]}]},{"name":"Shenzhen Science and Technology Innovation Commission","award":["R2020A045"],"award-info":[{"award-number":["R2020A045"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872310, 62102131"],"award-info":[{"award-number":["61872310, 62102131"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20210361"],"award-info":[{"award-number":["BK20210361"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,7,10]]},"DOI":"10.1145\/3489517.3530417","type":"proceedings-article","created":{"date-parts":[[2022,8,23]],"date-time":"2022-08-23T23:19:29Z","timestamp":1661296769000},"page":"193-198","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Sign bit is enough"],"prefix":"10.1145","author":[{"given":"Feijie","family":"Wu","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiqi","family":"He","sequence":"additional","affiliation":[{"name":"The University of British Columbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Guo","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihao","family":"Qu","sequence":"additional","affiliation":[{"name":"Hohai University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haozhao","family":"Wang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weihua","family":"Zhuang","sequence":"additional","affiliation":[{"name":"University of Waterloo"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,8,23]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Object detection binary classifiers methodology based on deep learning to identify small objects handled similarly: Application in video surveillance,\" Knowledge-Based Systems","author":"P\u00e9rez-Hern\u00e1ndez F.","year":"2020","unstructured":"F. P\u00e9rez-Hern\u00e1ndez, S. Tabik, A. Lamas, R. Olmos, H. Fujita, and F. Herrera, \"Object detection binary classifiers methodology based on deep learning to identify small objects handled similarly: Application in video surveillance,\" Knowledge-Based Systems, 2020."},{"key":"e_1_3_2_1_2_1","volume-title":"Application of natural language processing in healthcare,\" Computational Intelligence and Healthcare Informatics","author":"Roy K.","year":"2021","unstructured":"K. Roy, S. Debdas, S. Kundu, S. Chouhan, S. Mohanty, and B. Biswas, \"Application of natural language processing in healthcare,\" Computational Intelligence and Healthcare Informatics, 2021."},{"key":"e_1_3_2_1_3_1","volume-title":"Bernstein et al., \"Imagenet large scale visual recognition challenge,\" International journal of computer vision","author":"Russakovsky O.","year":"2015","unstructured":"O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein et al., \"Imagenet large scale visual recognition challenge,\" International journal of computer vision, 2015."},{"key":"e_1_3_2_1_4_1","volume-title":"https:\/\/github.com\/baidu-research\/tensorflow-allreduce","year":"2017","unstructured":"Baidu-Research, \"tensorflow-allreduce,\" [Source Code]. https:\/\/github.com\/baidu-research\/tensorflow-allreduce, 2017."},{"key":"e_1_3_2_1_5_1","volume-title":"fast and easy distributed deep learning in tensorflow,\" arXiv preprint arXiv:1802.05799","author":"Sergeev A.","year":"2018","unstructured":"A. Sergeev and M. Del Balso, \"Horovod: fast and easy distributed deep learning in tensorflow,\" arXiv preprint arXiv:1802.05799, 2018."},{"key":"e_1_3_2_1_6_1","volume-title":"Massively distributed sgd: Imagenet\/resnet-50 training in a flash,\" arXiv preprint arXiv:1811.05233","author":"Mikami H.","year":"2018","unstructured":"H. Mikami, H. Suganuma, P. U-chupala, Y. Tanaka, and Y. Kageyama, \"Massively distributed sgd: Imagenet\/resnet-50 training in a flash,\" arXiv preprint arXiv:1811.05233, 2018."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"M. Li D. G. Andersen J. W. Park A. J. Smola A. Ahmed V. Josifovski J. Long E. J. Shekita and B.-Y. Su \"Scaling distributed machine learning with the parameter server \" in OSDI 2014.","DOI":"10.1145\/2640087.2644155"},{"key":"e_1_3_2_1_8_1","unstructured":"Y. Lu and C. De Sa \"Optimal complexity in decentralized training \" in ICML 2021."},{"key":"e_1_3_2_1_9_1","volume-title":"Quasi-global momentum: Accelerating decentralized deep learning on heterogeneous data,\" in ICML","author":"Lin T.","year":"2021","unstructured":"T. Lin, S. P. Karimireddy, S. U. Stich, and M. Jaggi, \"Quasi-global momentum: Accelerating decentralized deep learning on heterogeneous data,\" in ICML, 2021."},{"key":"e_1_3_2_1_10_1","volume-title":"Accelerating gossip sgd with periodic global averaging,\" in ICML","author":"Chen Y.","year":"2021","unstructured":"Y. Chen, K. Yuan, Y. Zhang, P. Pan, Y. Xu, and W. Yin, \"Accelerating gossip sgd with periodic global averaging,\" in ICML, 2021."},{"key":"e_1_3_2_1_11_1","volume-title":"Deep residual learning for image recognition,\" in CVPR","author":"He K.","year":"2016","unstructured":"K. He, X. Zhang, S. Ren, and J. Sun, \"Deep residual learning for image recognition,\" in CVPR, 2016."},{"key":"e_1_3_2_1_12_1","volume-title":"Askell et al., \"Language models are few-shot learners,\" in NeurIPS","author":"Brown T. B.","year":"2020","unstructured":"T. B. Brown, B. Mann, N. Ryder, M. Subbiah, J. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell et al., \"Language models are few-shot learners,\" in NeurIPS, 2020."},{"key":"e_1_3_2_1_13_1","volume-title":"signsgd with majority vote is communication efficient and fault tolerant,\" in ICLR","author":"Bernstein J.","year":"2018","unstructured":"J. Bernstein, J. Zhao, K. Azizzadenesheli, and A. Anandkumar, \"signsgd with majority vote is communication efficient and fault tolerant,\" in ICLR, 2018."},{"key":"e_1_3_2_1_14_1","volume-title":"Stochastic sign descent methods: New algorithms and better theory,\" in ICML","author":"Safaryan M.","year":"2021","unstructured":"M. Safaryan and P. Richt\u00e1rik, \"Stochastic sign descent methods: New algorithms and better theory,\" in ICML, 2021."},{"key":"e_1_3_2_1_15_1","volume-title":"signsgd via zeroth-order oracle,\" in ICLR","author":"Liu S.","year":"2018","unstructured":"S. Liu, P.-Y. Chen, X. Chen, and M. Hong, \"signsgd via zeroth-order oracle,\" in ICLR, 2018."},{"key":"e_1_3_2_1_16_1","volume-title":"1-bit adam: Communication efficient large-scale training with adam's convergence speed,\" in ICML","author":"Tang H.","year":"2021","unstructured":"H. Tang, S. Gan, A. A. Awan, S. Rajbhandari, C. Li, X. Lian, J. Liu, C. Zhang, and Y. He, \"1-bit adam: Communication efficient large-scale training with adam's convergence speed,\" in ICML, 2021."},{"key":"e_1_3_2_1_17_1","volume-title":"Terngrad: Ternary gradients to reduce communication in distributed deep learning,\" in NeurIPS","author":"Wen W.","year":"2017","unstructured":"W. Wen, C. Xu, F. Yan, C. Wu, Y. Wang, Y. Chen, and H. Li, \"Terngrad: Ternary gradients to reduce communication in distributed deep learning,\" in NeurIPS, 2017."},{"key":"e_1_3_2_1_18_1","volume-title":"Qsgd: Communication-efficient sgd via gradient quantization and encoding,\" in NeurIPS","author":"Alistarh D.","year":"2017","unstructured":"D. Alistarh, D. Grubic, J. Li, R. Tomioka, and M. Vojnovic, \"Qsgd: Communication-efficient sgd via gradient quantization and encoding,\" in NeurIPS, 2017."},{"key":"e_1_3_2_1_19_1","volume-title":"Zipml: Training linear models with end-to-end low precision, and a little bit of deep learning,\" in ICML","author":"Zhang H.","year":"2017","unstructured":"H. Zhang, J. Li, K. Kara, D. Alistarh, J. Liu, and C. Zhang, \"Zipml: Training linear models with end-to-end low precision, and a little bit of deep learning,\" in ICML, 2017."},{"key":"e_1_3_2_1_20_1","volume-title":"Gradiveq: Vector quantization for bandwidth-efficient gradient aggregation in distributed cnn training,\" in NeurIPS","author":"Yu M.","year":"2018","unstructured":"M. Yu, Z. Lin, K. Narra, S. Li, Y. Li, N. S. Kim, A. Schwing, M. Annavaram, and S. Avestimehr, \"Gradiveq: Vector quantization for bandwidth-efficient gradient aggregation in distributed cnn training,\" in NeurIPS, 2018."},{"key":"e_1_3_2_1_21_1","volume-title":"signsgd: Compressed optimisation for non-convex problems,\" in ICML","author":"Bernstein J.","year":"2018","unstructured":"J. Bernstein, Y.-X. Wang, K. Azizzadenesheli, and A. Anandkumar, \"signsgd: Compressed optimisation for non-convex problems,\" in ICML, 2018."},{"key":"e_1_3_2_1_22_1","volume-title":"Gradient sparsification for communication-efficient distributed optimization,\" in NeurIPS","author":"Wangni J.","year":"2018","unstructured":"J. Wangni, J. Wang, J. Liu, and T. Zhang, \"Gradient sparsification for communication-efficient distributed optimization,\" in NeurIPS, 2018."},{"key":"e_1_3_2_1_23_1","volume-title":"Tail: an automated and lightweight gradient compression framework for distributed deep learning,\" in DAC","author":"Guo J.","year":"2020","unstructured":"J. Guo, S. Hu, W. Wang, C. Yao, J. Han, R. Li, and Y. Lu, \"Tail: an automated and lightweight gradient compression framework for distributed deep learning,\" in DAC, 2020."},{"key":"e_1_3_2_1_24_1","volume-title":"Powersgd: Practical low-rank gradient compression for distributed optimization,\" NeurIPS","author":"Vogels T.","year":"2019","unstructured":"T. Vogels, S. P. Karinireddy, and M. Jaggi, \"Powersgd: Practical low-rank gradient compression for distributed optimization,\" NeurIPS, 2019."},{"key":"e_1_3_2_1_25_1","volume-title":"Yu et al., \"Highly scalable deep learning training system with mixed-precision: Training imagenet in four minutes,\" arXiv preprint arXiv:1807.11205","author":"Jia X.","year":"2018","unstructured":"X. Jia, S. Song, W. He, Y. Wang, H. Rong, F. Zhou, L. Xie, Z. Guo, Y. Yang, L. Yu et al., \"Highly scalable deep learning training system with mixed-precision: Training imagenet in four minutes,\" arXiv preprint arXiv:1807.11205, 2018."},{"key":"e_1_3_2_1_26_1","volume-title":"Hinton et al., \"Learning multiple layers of features from tiny images","author":"Krizhevsky A.","year":"2009","unstructured":"A. Krizhevsky, G. Hinton et al., \"Learning multiple layers of features from tiny images,\" 2009."},{"key":"e_1_3_2_1_27_1","volume-title":"Learning word vectors for sentiment analysis,\" in Annual Meeting of the Association for Computational Linguistics: Human Language Technologies","author":"Maas A. L.","year":"2011","unstructured":"A. L. Maas, R. E. Daly, P. T. Pham, D. Huang, A. Y. Ng, and C. Potts, \"Learning word vectors for sentiment analysis,\" in Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, 2011."},{"key":"e_1_3_2_1_28_1","volume-title":"Imagenet classification with deep convolutional neural networks,\" NeurIPS","author":"Krizhevsky A.","year":"2012","unstructured":"A. Krizhevsky, I. Sutskever, and G. E. Hinton, \"Imagenet classification with deep convolutional neural networks,\" NeurIPS, 2012."},{"key":"e_1_3_2_1_29_1","volume-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter,\" arXiv preprint arXiv:1910.01108","author":"Sanh V.","year":"2019","unstructured":"V. Sanh, L. Debut, J. Chaumond, and T. Wolf, \"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter,\" arXiv preprint arXiv:1910.01108, 2019."},{"key":"e_1_3_2_1_30_1","volume-title":"Error feedback fixes signsgd and other gradient compression schemes,\" in ICML","author":"Karimireddy S. P.","year":"2019","unstructured":"S. P. Karimireddy, Q. Rebjock, S. Stich, and M. Jaggi, \"Error feedback fixes signsgd and other gradient compression schemes,\" in ICML, 2019."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"P. Elias \"Universal codeword sets and representations of the integers \" IEEE transactions on information theory 1975.","DOI":"10.1109\/TIT.1975.1055349"}],"event":{"name":"DAC '22: 59th ACM\/IEEE Design Automation Conference","location":"San Francisco California","acronym":"DAC '22","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CEDA"]},"container-title":["Proceedings of the 59th ACM\/IEEE Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3489517.3530417","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3489517.3530417","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:39Z","timestamp":1750191519000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3489517.3530417"}},"subtitle":["a learning synchronization framework for multi-hop all-reduce with ultimate compression"],"short-title":[],"issued":{"date-parts":[[2022,7,10]]},"references-count":31,"alternative-id":["10.1145\/3489517.3530417","10.1145\/3489517"],"URL":"https:\/\/doi.org\/10.1145\/3489517.3530417","relation":{},"subject":[],"published":{"date-parts":[[2022,7,10]]},"assertion":[{"value":"2022-08-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}