{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:37:59Z","timestamp":1782833879498,"version":"3.54.5"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030185787","type":"print"},{"value":"9783030185794","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-18579-4_9","type":"book-chapter","created":{"date-parts":[[2019,4,23]],"date-time":"2019-04-23T15:05:36Z","timestamp":1556031936000},"page":"139-155","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Sparse Gradient Compression for Distributed SGD"],"prefix":"10.1007","author":[{"given":"Haobo","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingxia","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Lei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,4,24]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Bottou, L.: Large-scale machine learning with stochastic gradient descent. In: COMPSTAT\u20192010, pp. 177\u2013186. Physica-Verlag HD (2010)","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"9_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1007\/978-3-319-55705-2_20","volume-title":"Database Systems for Advanced Applications","author":"Y Li","year":"2017","unstructured":"Li, Y., Chen, Z., Cai, Y., Huang, D., Li, Q.: Accelerating convolutional neural networks using fine-tuned backpropagation progress. In: Bao, Z., Trajcevski, G., Chang, L., Hua, W. (eds.) DASFAA 2017. LNCS, vol. 10179, pp. 256\u2013266. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-55705-2_20"},{"key":"9_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1007\/978-3-319-91458-9_43","volume-title":"Database Systems for Advanced Applications","author":"K Zhao","year":"2018","unstructured":"Zhao, K., Zhang, J., Zhang, L., Li, C., Chen, H.: CDSFM: a circular distributed SGLD-based factorization machines. In: Pei, J., Manolopoulos, Y., Sadiq, S., Li, J. (eds.) DASFAA 2018. LNCS, vol. 10828, pp. 701\u2013709. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-91458-9_43"},{"issue":"4","key":"9_CR4","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1007\/s41019-017-0032-6","volume":"1","author":"K Wang","year":"2016","unstructured":"Wang, K., Peng, H., Jin, Y., Sha, C., Wang, X.: Local weighted matrix factorization for top-n recommendation with implicit feedback. Data Sci. Eng. 1(4), 252\u2013264 (2016)","journal-title":"Data Sci. Eng."},{"issue":"3","key":"9_CR5","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1207\/s15327752jpa6803_3","volume":"68","author":"LJ Davis","year":"1997","unstructured":"Davis, L.J., Offord, K.P.: Logistic regression. J. Pers. Assess. 68(3), 497\u2013507 (1997)","journal-title":"J. Pers. Assess."},{"issue":"4","key":"9_CR6","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/5254.708428","volume":"13","author":"MA Hearst","year":"1998","unstructured":"Hearst, M.A., Dumais, S.T., Osuna, E., Platt, J., Scholkopf, B.: Support vector machines. IEEE Intell. Syst. Appl. 13(4), 18\u201328 (1998)","journal-title":"IEEE Intell. Syst. Appl."},{"key":"9_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/978-3-319-55699-4_17","volume-title":"Database Systems for Advanced Applications","author":"J Jiang","year":"2017","unstructured":"Jiang, J., Zhang, Z., Cui, B., Tong, Y., Xu, N.: StroMAX: partitioning-based scheduler for real-time stream processing system. In: Candan, S., Chen, L., Pedersen, T.B., Chang, L., Hua, W. (eds.) DASFAA 2017. LNCS, vol. 10178, pp. 269\u2013288. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-55699-4_17"},{"issue":"2","key":"9_CR8","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1007\/s41019-018-0065-5","volume":"3","author":"M Bhuiyan","year":"2018","unstructured":"Bhuiyan, M., Hasan, M.A.: Representing graphs as bag of vertices and partitions for graph classification. Data Sci. Eng. 3(2), 150\u2013165 (2018)","journal-title":"Data Sci. Eng."},{"key":"9_CR9","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J Schmidhuber","year":"2015","unstructured":"Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85\u2013117 (2015)","journal-title":"Neural Netw."},{"key":"9_CR10","unstructured":"Lin, Y., Han, S., Mao, H., Wang, Y., Dally, B.: Deep gradient compression: reducing the communication bandwidth for distributed training. In: ICLR (2018)"},{"key":"9_CR11","unstructured":"Tsuzuku, Y., Imachi, H., Akiba, H.: Variance-based gradient compression for efficient distributed deep learning. arXiv preprint arXiv:1802.06058 (2018)"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Jiang, J., Fu, F., Yang, T., Cui, B.: SketchML: accelerating distributed machine learning with data sketches. In: SIGMOD, pp. 1269\u20131284. ACM (2018)","DOI":"10.1145\/3183713.3196894"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Strom, N.: Scalable distributed DNN training using commodity GPU cloud computing. In: INTERSPEECH (2015)","DOI":"10.21437\/Interspeech.2015-354"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Aji, A.F., Heafield, K.: Sparse communication for distributed gradient descent. In: EMNLP, pp. 440\u2013445. Association for Computational Linguistics (2017)","DOI":"10.18653\/v1\/D17-1045"},{"key":"9_CR15","unstructured":"Wangni, J., Wang, J., Liu, J., Zhang, T.: Gradient sparsification for communication-efficient distributed optimization. arXiv preprint arXiv:1710.09854 (2017)"},{"key":"9_CR16","unstructured":"Reddi, S.J., Kale, S., Kumar, S.: On the convergence of adam and beyond. In: ICLR (2018)"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Seide, F., Fu, H., Droppo, J., Li, G., Yu, D.: 1-bit stochastic gradient descent and its application to data-parallel distributed training of speech DNNs. In: INTERSPEECH (2014)","DOI":"10.21437\/Interspeech.2014-274"},{"key":"9_CR18","unstructured":"Alistarh, D., Grubic, D., Li, J., Tomioka, R., Vojnovic, M.: QSGD: communication-efficient SGD via gradient quantization and encoding. In: NIPS, pp. 1709\u20131720. Curran Associates Inc. (2017)"},{"key":"9_CR19","unstructured":"Wu, J., Huang, W., Huang, J., Zhang, T.: Error compensated quantized SGD and its applications to large-scale distributed optimization. In: ICML, pp. 5321\u20135329 (2018)"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Dryden, N., Moon, T., Jacobs, S.A., Essen, B.V.: Communication quantization for data-parallel training of deep neural networks. In: MLHPC, pp. 1\u20138. IEEE (2016)","DOI":"10.1109\/MLHPC.2016.004"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Chen, C.-Y., Choi, J., Brand, D., Agrawal, A., Zhang, W., Gopalakrishnan, K.: Adacomp: adaptive residual gradient compression for data-parallel distributed training. In: AAAI, pp. 2827\u20132835 (2018)","DOI":"10.1609\/aaai.v32i1.11728"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Mitliagkas, I., Zhang, C., Hadjis, S., R\u00e9, C.: Asynchrony begets momentum, with an application to deep learning. In: Allerton, pp. 997\u20131004. IEEE (2016)","DOI":"10.1109\/ALLERTON.2016.7852343"},{"key":"9_CR23","unstructured":"Zhang, W., Gupta, S., Lian, X., Liu, J.: Staleness-aware async-SGD for distributed deep learning. In: IJCAI, pp. 2350\u20132356. AAAI Press (2016)"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Jiang, J., Cui, B., Zhang, C., Yu, L.: Heterogeneity-aware distributed parameter servers. In: SIGMOD, pp. 463\u2013478. ACM (2017)","DOI":"10.1145\/3035918.3035933"},{"issue":"5","key":"9_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0041-5553(64)90137-5","volume":"4","author":"BT Polyak","year":"1964","unstructured":"Polyak, B.T.: Some methods of speeding up the convergence of iteration methods. USSR Comput. Math. Math. Phys. 4(5), 1\u201317 (1964)","journal-title":"USSR Comput. Math. Math. Phys."},{"key":"9_CR26","unstructured":"McMahan, B., Streeter, M.: Delay-tolerant algorithms for asynchronous distributed online learning. In: NIPS, pp. 2915\u20132923 (2014)"},{"key":"9_CR27","unstructured":"Nesterov, Y., et al.: Gradient methods for minimizing composite objective function (2007)"},{"key":"9_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/978-3-319-30671-1_4","volume-title":"Advances in Information Retrieval","author":"W Zhang","year":"2016","unstructured":"Zhang, W., Du, T., Wang, J.: Deep learning over multi-field categorical data. In: Ferro, N., et al. (eds.) ECIR 2016. LNCS, vol. 9626, pp. 45\u201357. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-30671-1_4"},{"issue":"2","key":"9_CR29","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1093\/nsr\/nwx018","volume":"5","author":"J Jiang","year":"2017","unstructured":"Jiang, J., Lele, Y., Jiang, J., Liu, Y., Cui, B.: Angel: a new large-scale machine learning system. Natl. Sci. Rev. 5(2), 216\u2013236 (2017)","journal-title":"Natl. Sci. Rev."},{"issue":"11","key":"9_CR30","doi-asserted-by":"publisher","first-page":"1406","DOI":"10.14778\/3137628.3137649","volume":"10","author":"Y Lele","year":"2017","unstructured":"Lele, Y., Zhang, C., Shao, Y., Cui, B.: LDA*: a robust and large-scale topic modeling system. Proc. VLDB Endowment 10(11), 1406\u20131417 (2017)","journal-title":"Proc. VLDB Endowment"}],"container-title":["Lecture Notes in Computer Science","Database Systems for Advanced Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-18579-4_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T08:49:25Z","timestamp":1710233365000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-18579-4_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030185787","9783030185794"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-18579-4_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"24 April 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DASFAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Database Systems for Advanced Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chiang Mai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 April 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 April 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dasfaa2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/dasfaa2019.eng.cmu.ac.th\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"501","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"92","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"64","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"18% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"13 demo papers, 6 tutorial papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}