{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:30:03Z","timestamp":1775230203208,"version":"3.50.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030805982","type":"print"},{"value":"9783030805999","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-80599-9_2","type":"book-chapter","created":{"date-parts":[[2021,6,19]],"date-time":"2021-06-19T11:03:43Z","timestamp":1624100623000},"page":"15-23","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Scaling Federated Learning for Fine-Tuning of Large Language Models"],"prefix":"10.1007","author":[{"given":"Agrin","family":"Hilmkil","sequence":"first","affiliation":[]},{"given":"Sebastian","family":"Callh","sequence":"additional","affiliation":[]},{"given":"Matteo","family":"Barbieri","sequence":"additional","affiliation":[]},{"given":"Leon Ren\u00e9","family":"S\u00fctfeld","sequence":"additional","affiliation":[]},{"given":"Edvin Listo","family":"Zec","sequence":"additional","affiliation":[]},{"given":"Olof","family":"Mogren","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,6,20]]},"reference":[{"key":"2_CR1","unstructured":"Adhikari, A., Ram, A., Tang, R., Lin, J.: DocBERT: BERT for document classification. arXiv preprint arXiv:1904.08398 (2019)"},{"key":"2_CR2","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (1), pp. 4171\u20134186 (2019)"},{"key":"2_CR3","unstructured":"Ge, S., Wu, F., Wu, C., Qi, T., Huang, Y., Xie, X.: FedNER: medical named entity recognition with federated learning. arXiv preprint arXiv:2003.09288 (2020)"},{"key":"2_CR4","unstructured":"Guha, N., Talwalkar, A., Smith, V.: One-shot federated learning. arXiv preprint arXiv:1902.11175 (2019)"},{"key":"2_CR5","unstructured":"Hard, A., et al.: Federated learning for mobile keyboard prediction. CoRR abs\/1811.03604 (2018)"},{"key":"2_CR6","unstructured":"Hsu, T.M.H., Qi, H., Brown, M.: Measuring the effects of non-identical data distribution for federated visual classification. arXiv preprint arXiv:1909.06335 (2019)"},{"key":"2_CR7","unstructured":"Karimireddy, S.P., Kale, S., Mohri, M., Reddi, S.J., Stich, S.U., Suresh, A.T.: Scaffold: stochastic controlled averaging for on-device federated learning. arXiv preprint arXiv:1910.06378 (2019)"},{"key":"2_CR8","unstructured":"Kone\u010dn\u1ef3, J., McMahan, B., Ramage, D.: Federated optimization: distributed optimization beyond the datacenter. arXiv preprint arXiv:1511.03575 (2015)"},{"key":"2_CR9","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: ALBERT: a lite BERT for self-supervised learning of language representations. In: International Conference on Learning Representations (2020)"},{"issue":"4","key":"2_CR10","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee, J., et al.: BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36(4), 1234\u20131240 (2020)","journal-title":"Bioinformatics"},{"key":"2_CR11","unstructured":"Li, T., Sanjabi, M., Beirami, A., Smith, V.: Fair resource allocation in federated learning. arXiv preprint arXiv:1905.10497 (2019)"},{"key":"2_CR12","unstructured":"Lin, T., Kong, L., Stich, S.U., Jaggi, M.: Ensemble distillation for robust model fusion in federated learning. arXiv preprint arXiv:2006.07242 (2020)"},{"key":"2_CR13","unstructured":"Listo Zec, E., Mogren, O., Martinsson, J., S\u00fctfeld, L.R., Gillblad, D.: Federated learning using a mixture of experts (2020)"},{"key":"2_CR14","unstructured":"Liu, D., Miller, T.: Federated pretraining and fine tuning of BERT using clinical notes from multiple silos (2020)"},{"key":"2_CR15","unstructured":"Maas, A.L., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., Potts, C.: Learning word vectors for sentiment analysis. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Portland, Oregon, USA, pp. 142\u2013150. Association for Computational Linguistics, June 2011"},{"key":"2_CR16","unstructured":"McMahan, B., Moore, E., Ramage, D., Hampson, S., Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Singh, A., Zhu, J. (eds.) Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, vol. 54, , Fort Lauderdale, FL, USA, pp. 1273\u20131282. PMLR, 20\u201322 April 2017"},{"key":"2_CR17","unstructured":"McMahan, H.B., Ramage, D., Talwar, K., Zhang, L.: Learning differentially private recurrent language models. arXiv preprint arXiv:1710.06963 (2017)"},{"key":"2_CR18","unstructured":"Mohri, M., Sivek, G., Suresh, A.T.: Agnostic federated learning. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of Machine Learning Research, Long Beach, California, USA, vol. 97, pp. 4615\u20134625. PMLR, 09\u201315 June 2019"},{"key":"2_CR19","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019 Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32, pp. 8024\u20138035. Curran Associates, Inc. (2019)"},{"key":"2_CR20","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. In: EMC$$^2$$ Workshop at NeurIPS 2019 (2019)"},{"key":"2_CR21","unstructured":"Sun, C., Huang, L., Qiu, X.: Utilizing BERT for aspect-based sentiment analysis via constructing auxiliary sentence. arXiv preprint arXiv:1903.09588 (2019)"},{"key":"2_CR22","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/978-3-030-32381-3_16","volume-title":"Chinese Computational Linguistics","author":"C Sun","year":"2019","unstructured":"Sun, C., Qiu, X., Xu, Y., Huang, X.: How to fine-tune BERT for text classification? In: Sun, M., Huang, X., Ji, H., Liu, Z., Liu, Y. (eds.) CCL 2019. LNCS (LNAI), vol. 11856, pp. 194\u2013206. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32381-3_16"},{"key":"2_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"2_CR24","unstructured":"Wolf, T., et al.: HuggingFace\u2019s transformers: state-of-the-art natural language processing. arXiv abs\/1910.03771 (2019)"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Yang, W., et al.: End-to-end open-domain question answering with BERTserini. arXiv preprint arXiv:1902.01718 (2019)","DOI":"10.18653\/v1\/N19-4013"},{"issue":"1","key":"2_CR26","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1109\/TCBB.2018.2849968","volume":"16","author":"Z Zeng","year":"2018","unstructured":"Zeng, Z., Deng, Y., Li, X., Naumann, T., Luo, Y.: Natural language processing for EHR-based computational phenotyping. IEEE\/ACM Trans. Comput. Biol. Bioinf. 16(1), 139\u2013153 (2018)","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinf."},{"key":"2_CR27","unstructured":"Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems 28, pp. 649\u2013657. Curran Associates, Inc. (2015)"},{"key":"2_CR28","unstructured":"Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., Chandra, V.: Federated learning with non-IID data. arXiv preprint arXiv:1806.00582 (2018)"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-80599-9_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,5]],"date-time":"2023-11-05T03:45:08Z","timestamp":1699155908000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-80599-9_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030805982","9783030805999"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-80599-9_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"20 June 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLDB","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Applications of Natural Language to Information Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Saarbr\u00fccken","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 June 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nldb2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/nldb2021.sb.dfki.de\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"82","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":"19","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":"14","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":"23% - 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":"5","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":"The conference was held virtually.","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)"}}]}}