{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T15:20:59Z","timestamp":1743088859876,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031213946"},{"type":"electronic","value":"9783031213953"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-21395-3_15","type":"book-chapter","created":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T14:34:17Z","timestamp":1670250857000},"page":"155-167","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["TrainFlow: A Lightweight, Programmable ML Training Framework via Serverless Paradigm"],"prefix":"10.1007","author":[{"given":"Wenting","family":"Tan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengyu","family":"Lei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cunchi","family":"Lv","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,1]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"You, Y., Zhang, Z., Hsieh, C., Demmel, J., Keutzer, K.: ImageNet training in minutes. In: The 47th International Conference on Parallel Processing (ICPP \u201918) (2018)","DOI":"10.1145\/3225058.3225069"},{"key":"15_CR2","unstructured":"Yuan, J., Li, X., Cheng, C., Liu, J., Guo, R., Cai, S., et al.: Oneflow: redesign the distributed deep learning framework from scratch. arXiv preprint arXiv:2110.15032 (2021)"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Harlap, A., Narayanan, D., Phanishayee, A., Seshadri, V., Devanur, N., Ganger, G., et al.: Pipedream: fast and efficient pipeline parallel DNN training. arXiv preprint arXiv:1806.03377 (2018)","DOI":"10.1145\/3341301.3359646"},{"key":"15_CR4","unstructured":"Mai, L., Li, G., Wagenl\u00e4nder, M., Fertakis, K., Brabete, A.O., Piezuch, P.: KungFu: marking training in distributed machine learning adaptive. In: The 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201920) (2020)"},{"key":"15_CR5","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., et al.: TensorFlow: a system for large-scale machine learning. In: The 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201916) (2016)"},{"key":"15_CR6","unstructured":"Jiang, Y., Zhu, Y., Lan, C., Yi, B., Cui, Y., Guo, C.: A unified architecture for accelerating distributed DNN training in heterogeneous GPU\/CPU clusters. In: The 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201920) (2020)"},{"key":"15_CR7","unstructured":"Wang, G., Venkataraman, S., Phanishayee, A., Devanur, N., Thelin, J., Stoica, I.: Blink: fast and generic collectives for distributed ML. CoRR, abs\/1910.04940 (2019)"},{"key":"15_CR8","unstructured":"Cipar, J., Ho, Q., Kim, J.K., Lee, S., Ganger, G.R., Gibson, G., et al.: Solving the straggler problem with bounded staleness. In: The 2013 Workshop on Hot Topics in Operating Systems (HotOS \u201913) (2013)"},{"key":"15_CR9","unstructured":"Wagenl\u00e4nder, M., Mai, L., Li, G., Pietzuch, P.: Spotnik: designing distributed machine learning for transient cloud resources. In: The 12th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud \u201920) (2020)"},{"key":"15_CR10","unstructured":"Jia, X., Song, S., He, W., Wang, Y., Rong, H., Zhou, F., et al.: Highly scalable deep learning training system with mixed-precision: training ImageNet in four minutes. arXiv preprint arXiv:1807.11205 (2018)"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Wang, H., Niu, D., Li, B.: Distributed machine learning with a serverless architecture. In: The 2019 IEEE International Conference on Computer Communications (INFOCOM \u201919) (2019)","DOI":"10.1109\/INFOCOM.2019.8737391"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Carreira, J., Fonseca, P., Tumanov, A., Zhang, A., Katz, R.:. Cirrus: a serverless framework for end-to-end ML workflows. In: The 2019 ACM Symposium on Cloud Computing (SoCC \u201919) (2019)","DOI":"10.1145\/3357223.3362711"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, J., Gan, S., Liu, Y., Wang, F., Alonse, G., Klimovic, A., et al.: Towards demystifying serverless machine learning training. In: The 2021 ACM International Conference on Management of Data (SIGMOD \u201921) (2021)","DOI":"10.1145\/3448016.3459240"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"S\u00e1nchez-Artigas, M., Sarroca, P.: Experience paper: towards enhancing cost efficiency in serverless machine learning training. In: The 22nd ACM International Middleware Conference (Middleware \u201921) (2021)","DOI":"10.1145\/3464298.3494884"},{"key":"15_CR15","unstructured":"DAPR, Distributed Application Runtime. https:\/\/dapr.io\/. Accessed 18 March 2020"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Verbraeken, J., Wolting, M., Katzy, J., Kloppenburg, J., Verbelen, T., Rellermeyer, J.S.: A survey on distributed machine learning. ACM Computing Surveys (CSUR), 53(2), 1\u201333 (2020)","DOI":"10.1145\/3377454"},{"key":"15_CR17","unstructured":"Lian, X., Zhang, W., Zhang, C., Liu, J.: Asynchronous decentralized parallel stochastic gradient descent. In: The 35th International Conference on Machine Learning, PMLR 80 (2018)"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"L\u00f3pez, P.G., Arjona, A., Samp\u00e9, J., Slominski, A., Villard, L.: Triggerflow: trigger-based orchestration of serverless workflows. Future Gener. Comput. Syst. 124(1), 215\u2013229 (2021)","DOI":"10.1016\/j.future.2021.06.004"},{"key":"15_CR19","unstructured":"ElasticDL: A Kubernetes-native deep learning framework. https:\/\/elasticdl.github.io\/"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Barcelona-Pons, D., Sutra, P., S\u00e1nchez-Artigas, M., Par\u00eds, G., Garc\u00eda-L\u00f3pez, P.: Stateful serverless computing with crucial[J]. ACM Trans. Softw. Eng. Methodol. 31(3), 1\u201338 (2022)","DOI":"10.1145\/3490386"},{"key":"15_CR21","unstructured":"Sergeev, A., Balso, M.: Horovod: fast and easy distributed deep learning in TensorFlow. arXiv preprint arXiv:1802.05799 (2018)"}],"container-title":["Lecture Notes in Computer Science","Network and Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-21395-3_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T14:49:06Z","timestamp":1670251746000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-21395-3_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031213946","9783031213953"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-21395-3_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"1 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Network and Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jinan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"npc2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/npc2022.jlu.edu.cn\/","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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"89","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":"23","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":"8","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":"26% - 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":"6","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)"}}]}}