{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T18:18:41Z","timestamp":1781806721734,"version":"3.54.5"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,7,6]],"date-time":"2023-07-06T00:00:00Z","timestamp":1688601600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,7,6]],"date-time":"2023-07-06T00:00:00Z","timestamp":1688601600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003051","name":"New Energy and Industrial Technology Development Organization","doi-asserted-by":"publisher","award":["JPNP18010"],"award-info":[{"award-number":["JPNP18010"]}],"id":[{"id":"10.13039\/501100003051","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP18H03250"],"award-info":[{"award-number":["JP18H03250"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["21H03451"],"award-info":[{"award-number":["21H03451"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP22K19767"],"award-info":[{"award-number":["JP22K19767"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Hum-Cent Intell Syst"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Ensuring the transparency of machine learning models is vital for their ethical application in various industries. There has been a concurrent trend of distributed machine learning designed to limit access to training data for privacy concerns. Such models, trained over horizontally or vertically partitioned data, present a challenge for explainable AI because the explaining party may have a biased view of background data or a partial view of the feature space. As a result, explanations obtained from different participants of distributed machine learning might not be consistent with one another, undermining trust in the product. This paper presents an Explainable Data Collaboration Framework based on a model-agnostic additive feature attribution algorithm (KernelSHAP) and Data Collaboration method of privacy-preserving distributed machine learning. In particular, we present three algorithms for different scenarios of explainability in Data Collaboration and verify their consistency with experiments on open-access datasets. Our results demonstrated a significant (by at least a factor of 1.75) decrease in feature attribution discrepancies among the users of distributed machine learning. The proposed method improves consistency among explanations obtained from different participants, which can enhance trust in the product and enable ethical application in various industries.<\/jats:p>","DOI":"10.1007\/s44230-023-00032-4","type":"journal-article","created":{"date-parts":[[2023,7,6]],"date-time":"2023-07-06T06:02:26Z","timestamp":1688623346000},"page":"197-210","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["DC-SHAP Method for Consistent Explainability in Privacy-Preserving Distributed Machine Learning"],"prefix":"10.1007","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7468-882X","authenticated-orcid":false,"given":"Anna","family":"Bogdanova","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akira","family":"Imakura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tetsuya","family":"Sakurai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,7,6]]},"reference":[{"issue":"9","key":"32_CR1","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1038\/s42256-019-0088-2","volume":"1","author":"A Jobin","year":"2019","unstructured":"Jobin A, Ienca M, Vayena E. The global landscape of ai ethics guidelines. Nat Mach Intelli. 2019;1(9):389\u201399.","journal-title":"Nat Mach Intelli"},{"key":"32_CR2","first-page":"1350","volume":"88","author":"TD Grant","year":"2020","unstructured":"Grant TD, Wischik DJ. Show us the data: privacy, explainability, and why the law can\u2019t have both. Geo Wash L Rev. 2020;88:1350.","journal-title":"Geo Wash L Rev"},{"key":"32_CR3","first-page":"1","volume-title":"2020 57th ACM\/IEEE Design Automation Conference (DAC)","author":"H Chen","year":"2020","unstructured":"Chen H, Hussain SU, Boemer F, Stapf E, Sadeghi AR, Koushanfar F, Cammarota R. Developing privacy-preserving ai systems: the lessons learned. In: 2020 57th ACM\/IEEE Design Automation Conference (DAC). IEEE; 2020. p. 1\u20134."},{"issue":"12","key":"32_CR4","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1145\/3387107","volume":"63","author":"Y Cheng","year":"2020","unstructured":"Cheng Y, Liu Y, Chen T, Yang Q. Federated learning for privacy-preserving ai. Commun ACM. 2020;63(12):33\u20136.","journal-title":"Commun ACM"},{"issue":"2","key":"32_CR5","doi-asserted-by":"publisher","first-page":"04020018","DOI":"10.1061\/AJRUA6.0001058","volume":"6","author":"A Imakura","year":"2020","unstructured":"Imakura A, Sakurai T. Data collaboration analysis framework using centralization of individual intermediate representations for distributed data sets. ASCE-ASME J Risk Uncertain Eng Syst Part A Civil Eng. 2020;6(2):04020018.","journal-title":"ASCE-ASME J Risk Uncertain Eng Syst Part A Civil Eng"},{"issue":"4","key":"32_CR6","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1007\/s13347-018-0330-6","volume":"32","author":"J Zerilli","year":"2019","unstructured":"Zerilli J, Knott A, Maclaurin J, Gavaghan C. Transparency in algorithmic and human decision-making: is there a double standard? Philos Technolo. 2019;32(4):661\u201383.","journal-title":"Philos Technolo"},{"key":"32_CR7","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-91387-8_1","volume-title":"International Conference on Future Data and Security Engineering","author":"JH Yoo","year":"2021","unstructured":"Yoo JH, Jeong H, Lee J, Chung T-M. Federated learning: issues in medical application. In: International Conference on Future Data and Security Engineering. Springer; 2021. p. 3\u201322."},{"key":"32_CR8","unstructured":"B\u00e1rcena JLC, Daole M, Ducange P, Marcelloni F, Renda A, Ruffini F, Schiavo A. Fed-xai: federated learning of explainable artificial intelligence models. 2022."},{"key":"32_CR9","unstructured":"Jain A, Ravula M, Ghosh J. Biased models have biased explanations. arXiv preprint arXiv:2012.10986. 2020."},{"key":"32_CR10","unstructured":"Wang G. Interpret federated learning with shapley values. arXiv preprint arXiv:1905.04519. 2019."},{"key":"32_CR11","unstructured":"Papernot N, Song S, Mironov I, Raghunathan A, Talwar K, Erlingsson \u00da. Scalable private learning with pate. arXiv preprint arXiv:1802.08908. 2018."},{"key":"32_CR12","unstructured":"Kone\u010dn\u1ef3 J, McMahan HB, Yu FX, Richt\u00e1rik P, Suresh AT, Bacon D. Federated learning: strategies for improving communication efficiency. arXiv preprint arXiv:1610.05492. 2016."},{"issue":"3","key":"32_CR13","first-page":"1","volume":"13","author":"Q Yang","year":"2019","unstructured":"Yang Q, Liu Y, Cheng Y, Kang Y, Chen T, Yu H. Federated learning, synthesis lectures on artificial intelligence and machine. Learning. 2019;13(3):1\u2013207.","journal-title":"Learning"},{"key":"32_CR14","unstructured":"Li Q, Wen Z, He B. Federated learning systems: vision, hype and reality for data privacy and protection. 2019."},{"key":"32_CR15","unstructured":"Bogdanova A, Nakai A, Okada Y, Imakura A, Sakurai T. Federated learning system without model sharing through integration of dimensional reduced data representations. arXiv preprint arXiv:2011.06803. 2020."},{"key":"32_CR16","first-page":"14","volume-title":"Pacific Rim Knowledge Acquisition Workshop","author":"A Imakura","year":"2021","unstructured":"Imakura A, Ye X, Sakurai T. Collaborative data analysis: non-model sharing-type machine learning for distributed data. In: Pacific Rim Knowledge Acquisition Workshop. Springer; 2021. p. 14\u201329."},{"key":"32_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114891","volume":"177","author":"A Imakura","year":"2021","unstructured":"Imakura A, Inaba H, Okada Y, Sakurai T. Interpretable collaborative data analysis on distributed data. Expert Syst Appl. 2021;177: 114891.","journal-title":"Expert Syst Appl"},{"key":"32_CR18","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","volume":"58","author":"AB Arrieta","year":"2020","unstructured":"Arrieta AB, D\u00edaz-Rodr\u00edguez N, Del Ser J, Bennetot A, Tabik S, Barbado A, Garc\u00eda S, Gil-L\u00f3pez S, Molina D, Benjamins R, et al. Explainable artificial intelligence (xai): concepts, taxonomies, opportunities and challenges toward responsible ai. Inf fusion. 2020;58:82\u2013115.","journal-title":"Inf fusion"},{"key":"32_CR19","first-page":"3319","volume-title":"International Conference on Machine Learning","author":"M Sundararajan","year":"2017","unstructured":"Sundararajan M, Taly A, Yan Q. Axiomatic attribution for deep networks. In: International Conference on Machine Learning. PMLR; 2017. p. 3319\u201328."},{"key":"32_CR20","unstructured":"Ribeiro MT, Singh S, Guestrin C. Model-agnostic interpretability of machine learning. arXiv preprint arXiv:1606.05386. 2016."},{"key":"32_CR21","unstructured":"Lundberg S, Lee S-I. A unified approach to interpreting model predictions. arXiv preprint arXiv:1705.07874. 2017."},{"issue":"8","key":"32_CR22","doi-asserted-by":"publisher","first-page":"395","DOI":"10.3390\/info13080395","volume":"13","author":"A Renda","year":"2022","unstructured":"Renda A, Ducange P, Marcelloni F, Sabella D, Filippou MC, Nardini G, Stea G, Virdis A, Micheli D, Rapone D, et al. Federated learning of explainable ai models in 6g systems: towards secure and automated vehicle networking. Information. 2022;13(8):395.","journal-title":"Information"},{"issue":"5","key":"32_CR23","doi-asserted-by":"publisher","first-page":"1653","DOI":"10.1109\/TFUZZ.2022.3207607","volume":"31","author":"L Zhang","year":"2022","unstructured":"Zhang L, Shi Y, Chang Y-C, Lin C-T. Federated fuzzy neural network with evolutionary rule learning. IEEE Trans Fuzzy Syst. 2022;31(5):1653\u201364.","journal-title":"IEEE Trans Fuzzy Syst"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Wu Y, Cai S, Xiao X, Chen G, Ooi BC. Privacy preserving vertical federated learning for tree-based models. arXiv preprint arXiv:2008.06170. 2020.","DOI":"10.14778\/3407790.3407811"},{"key":"32_CR25","doi-asserted-by":"crossref","unstructured":"Fiosina J. Explainable federated learning for taxi travel time prediction. In: International conference on vehicle technology and intelligent transport systems (VEHITS2021). SCITEPRESS; 2021. p. 670\u20137.","DOI":"10.5220\/0010485600002932"},{"key":"32_CR26","first-page":"392","volume-title":"International Conference on Vehicle Technology and Intelligent Transport Systems, International Conference on Smart Cities and Green ICT Systems","author":"J Fiosina","year":"2022","unstructured":"Fiosina J. Interpretable privacy-preserving collaborative deep learning for taxi trip duration forecasting. In: International Conference on Vehicle Technology and Intelligent Transport Systems, International Conference on Smart Cities and Green ICT Systems. Springer; 2022. p. 392\u2013411."},{"key":"32_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2022.102474","volume":"126","author":"P Chen","year":"2022","unstructured":"Chen P, Du X, Lu Z, Wu J, Hung PC. Evfl: An explainable vertical federated learning for data-oriented artificial intelligence systems. J Syst Architect. 2022;126: 102474.","journal-title":"J Syst Architect"},{"key":"32_CR28","doi-asserted-by":"crossref","unstructured":"Zheng S, Cao Y, Yoshikawa M. Secure shapley value for cross-silo federated learning. arXiv preprint arXiv:2209.04856. 2022.","DOI":"10.14778\/3587136.3587141"},{"key":"32_CR29","unstructured":"Kohavi R. Scaling up the accuracy of naive-bayes classifiers: a decision-tree hybrid. In: Second international conference on knowledge discovery and data mining, vol. 96. AAAI Press; 1996. p. 202\u20137."},{"key":"32_CR30","unstructured":"Dua D, Graff C. UCI Machine learning repository 2017. http:\/\/archive.ics.uci.edu\/ml. Accessed 5 Jan 2023."},{"key":"32_CR31","unstructured":"Smith JW, Everhart JE, Dickson W, Knowler WC, Johannes RS. Using the adap learning algorithm to forecast the onset of diabetes mellitus. In: Proceedings of the Annual Symposium on Computer Application in Medical Care. American Medical Informatics Association. 1988. p. 261."}],"container-title":["Human-Centric Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44230-023-00032-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44230-023-00032-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44230-023-00032-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,31]],"date-time":"2023-08-31T12:17:57Z","timestamp":1693484277000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44230-023-00032-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,6]]},"references-count":31,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,9]]}},"alternative-id":["32"],"URL":"https:\/\/doi.org\/10.1007\/s44230-023-00032-4","relation":{},"ISSN":["2667-1336"],"issn-type":[{"value":"2667-1336","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,6]]},"assertion":[{"value":"12 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 July 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}