{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T04:12:25Z","timestamp":1751515945028,"version":"3.41.0"},"reference-count":73,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T00:00:00Z","timestamp":1743552000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T00:00:00Z","timestamp":1743552000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Universidad Carlos III"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pattern Anal Applic"],"published-print":{"date-parts":[[2025,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Distributed machine learning approaches are required when training data cannot be collected in a central location, due to storage, transmission or privacy\/security constraints. An important task in any distributed machine learning context, and Federated Learning is no exception, is data value estimation or credit allocation, where the goal is to reward each participant proportionally to their contribution to the final performance of the machine learning model. However, all existing data value estimation techniques require that training be completed before the data values are obtained, and in this sense they can be considered as \u201ca posteriori\u201d approaches. Thus, all potential contributors must participate in the training process, regardless of the quality of their data or the final reward they can obtain. Here we present an \u201ca priori\u201d Shapley data value estimation technique in which, based on some statistical measures provided by the participants, the central counterpart or aggregator can obtain reasonably accurate data value estimates before actually starting the distributed learning process. To the best of our knowledge, this is the first \u201ca priori\u201d data value estimation approach proposed in the literature, and it can be used for the pre-selection of participants or to implement new pricing schemes. The introduced algorithms have been benchmarked using a variety of datasets and a logistic regression model, and we show that our \u201ca priori\u201d estimates are very accurate, compared to the centralized Shapley data values.<\/jats:p>","DOI":"10.1007\/s10044-025-01454-5","type":"journal-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T13:26:31Z","timestamp":1743773191000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["\u201cA priori\u201d shapley data value estimation"],"prefix":"10.1007","volume":"28","author":[{"given":"Angel","family":"Navia-V\u00e1zquez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jes\u00fas","family":"Cid-Sueiro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuel A.","family":"V\u00e1zquez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,2]]},"reference":[{"key":"1454_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103502","volume":"298","author":"K Aas","year":"2021","unstructured":"Aas K, Jullum M, L\u00f8land A (2021) Explaining individual predictions when features are dependent: More accurate approximations to shapley values. Artif Intell 298:103502. https:\/\/doi.org\/10.1016\/j.artint.2021.103502","journal-title":"Artif Intell"},{"key":"1454_CR2","doi-asserted-by":"publisher","first-page":"9226","DOI":"10.1609\/aaai.v37i8.26106","volume":"37","author":"M Amiri","year":"2023","unstructured":"Amiri M, Berdoz F, Raskar R (2023) Fundamentals of task-agnostic data valuation. Proc AAAI Conf Artif Intell 37:9226\u20139234. https:\/\/doi.org\/10.1609\/aaai.v37i8.26106","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"1454_CR3","doi-asserted-by":"publisher","unstructured":"Ardi\u00e7 E, Gen\u00e7 Y (2023) Data valuation methods for federated learning. In: 2023 31st Signal Processing and Communications Applications Conference (SIU), pp 1\u20134, https:\/\/doi.org\/10.1109\/SIU59756.2023.10223784","DOI":"10.1109\/SIU59756.2023.10223784"},{"key":"1454_CR4","unstructured":"Blackard J (1998) Covertype. http:\/\/archive.ics.uci.edu\/dataset\/31\/covertype"},{"key":"1454_CR5","doi-asserted-by":"publisher","unstructured":"Burgess M, Chapman A (2021) Approximating the shapley value using stratified empirical bernstein sampling. pp 73\u201381, https:\/\/doi.org\/10.24963\/ijcai.2021\/11","DOI":"10.24963\/ijcai.2021\/11"},{"key":"1454_CR6","doi-asserted-by":"publisher","first-page":"1726","DOI":"10.1016\/j.cor.2008.04.004","volume":"36","author":"J Castro","year":"2009","unstructured":"Castro J, Gomez D, Tejada J (2009) Polynomial calculation of the shapley value based on sampling. Comput Oper Res 36:1726\u20131730. https:\/\/doi.org\/10.1016\/j.cor.2008.04.004","journal-title":"Comput Oper Res"},{"key":"1454_CR7","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1162\/089976602753633402","volume":"14","author":"R Collobert","year":"2002","unstructured":"Collobert R, Bengio S, Bengio Y et al (2002) A parallel mixture of SVMs for very large scale problems. Neural Comput 14:1105\u20131114. https:\/\/doi.org\/10.1162\/089976602753633402","journal-title":"Neural Comput"},{"issue":"6","key":"1454_CR8","doi-asserted-by":"publisher","first-page":"1417","DOI":"10.1007\/s10115-022-01679-4","volume":"64","author":"Z Cong","year":"2022","unstructured":"Cong Z, Luo X, Pei J et al (2022) Data pricing in machine learning pipelines. Knowl Inf Syst 64(6):1417\u20131455","journal-title":"Knowl Inf Syst"},{"key":"1454_CR9","unstructured":"Council of European Union (2016) General Data Protection Regulation (GDPR) no.2016\/679"},{"key":"1454_CR10","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1016\/j.future.2023.05.007","volume":"147","author":"L Dong","year":"2023","unstructured":"Dong L, Liu Z, Zhang K et al (2023) Affordable federated edge learning framework via efficient shapley value estimation. Futur Gener Comput Syst 147:339\u2013349. https:\/\/doi.org\/10.1016\/j.future.2023.05.007","journal-title":"Futur Gener Comput Syst"},{"key":"1454_CR11","volume-title":"UCI Machine Learning Repository","author":"D Dua","year":"2019","unstructured":"Dua D, Graff C (2019) UCI Machine Learning Repository. University of California, School of Information and Computer Science, Irvine, CA"},{"key":"1454_CR12","unstructured":"European Commission (2014) Towards a thriving data-driven economy"},{"key":"1454_CR13","unstructured":"European Commission (2018) Guidance on Sharing Private Sector Data in the European Data Economy"},{"key":"1454_CR14","unstructured":"European Commission (2020) A European Strategy for Data"},{"key":"1454_CR15","doi-asserted-by":"publisher","unstructured":"Fan C, Liu P (2020) Federated Generative Adversarial Learning, pp 3\u201315. https:\/\/doi.org\/10.1007\/978-3-030-60636-7_1","DOI":"10.1007\/978-3-030-60636-7_1"},{"key":"1454_CR16","doi-asserted-by":"publisher","unstructured":"Fan Z, Fang H, Zhou Z et al (2022). Improving fairness for data valuation in horizontal federated learning. https:\/\/doi.org\/10.1109\/ICDE53745.2022.00228","DOI":"10.1109\/ICDE53745.2022.00228"},{"key":"1454_CR17","doi-asserted-by":"crossref","unstructured":"Fryer D, Str\u00fcmke I, Nguyen H (2021) Shapley values for feature selection: The good, the bad, and the axioms. arXiv: 2102.10936","DOI":"10.1109\/ACCESS.2021.3119110"},{"key":"1454_CR18","doi-asserted-by":"publisher","unstructured":"Fumagalli F, Muschalik M, Kolpaczki P, et al (2024) Kernelshap-iq: Weighted least-square optimization for shapley interactions. https:\/\/doi.org\/10.48550\/arXiv.2405.10852","DOI":"10.48550\/arXiv.2405.10852"},{"key":"1454_CR19","unstructured":"Ghorbani A, Zou J (2019) Data Shapley: Equitable Valuation of Data for Machine Learning. In: Proc. 36th International Conference on Machine Learning, PMLR, p 2242-2251"},{"key":"1454_CR20","doi-asserted-by":"publisher","unstructured":"Guo P, Yang Y, Guo W, et al (2024) A fair contribution measurement method for federated learning. Sensors 24(15). https:\/\/doi.org\/10.3390\/s24154967, https:\/\/www.mdpi.com\/1424-8220\/24\/15\/4967","DOI":"10.3390\/s24154967"},{"key":"1454_CR21","doi-asserted-by":"publisher","unstructured":"Hasan J (2023) Security and privacy issues of federated learning. https:\/\/doi.org\/10.48550\/arXiv.2307.12181","DOI":"10.48550\/arXiv.2307.12181"},{"key":"1454_CR22","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1007\/s10462-024-10846-8","volume":"57","author":"K Hu","year":"2024","unstructured":"Hu K, Gong S, Zhang Q (2024) An overview of implementing security and privacy in federated learning. Artif Intell Rev 57:204. https:\/\/doi.org\/10.1007\/s10462-024-10846-8","journal-title":"Artif Intell Rev"},{"key":"1454_CR23","doi-asserted-by":"publisher","unstructured":"Jethani N, Sudarshan M, Covert I, et al (2021) Fastshap: real-time shapley value estimation. https:\/\/doi.org\/10.48550\/arXiv.2107.07436","DOI":"10.48550\/arXiv.2107.07436"},{"key":"1454_CR24","doi-asserted-by":"crossref","unstructured":"Jia R, Dao D, Wang B, et al (2019) Efficient task-specific data valuation for nearest neighbor algorithms. ArXiv:1908.08619","DOI":"10.14778\/3342263.3342637"},{"key":"1454_CR25","unstructured":"Kone\u010dn\u00fd J, McMahan H, D. R, et al (2016) Federated optimization: Distributed machine learning for on-device intelligence. ArXiv 1610:02527"},{"key":"1454_CR26","unstructured":"Kurakin A, Goodfellow I, Bengio S (2017) Adversarial Machine Learning at Scale. In: Proceedings of the International Conference on Learning Representations (ICLR 2017)"},{"key":"1454_CR27","unstructured":"Kwon Y, Rivas MA, Zou J (2021) Efficient computation and analysis of distributional shapley values. In: Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, PMLR, pp 130:793\u2013801"},{"key":"1454_CR28","doi-asserted-by":"publisher","unstructured":"Lang K (1995) NewsWeeder: Learning to Filter Netnews. In: Proceedings of the 12th International Conference on Machine Learning (ICML-95). Morgan Kaufmann publishers Inc.: San Mateo, CA, USA, pp 331\u2013339, https:\/\/doi.org\/10.1016\/B978-1-55860-377-6.50048-7","DOI":"10.1016\/B978-1-55860-377-6.50048-7"},{"key":"1454_CR29","unstructured":"Lang news20 (1995) https:\/\/www.kaggle.com\/datasets\/thedevastator\/the-20-newsgroups-data-set-for-text-classificati"},{"key":"1454_CR30","doi-asserted-by":"publisher","unstructured":"LeCun Y, Bottou L, Bengio Y, et al (1998a) Gradient-based learning applied to document recognition. In: Proceedings of the IEEE, pp 2278\u20132324, https:\/\/doi.org\/10.1109\/5.726791","DOI":"10.1109\/5.726791"},{"key":"1454_CR31","unstructured":"LeCun Y, Cortes C, Burges CJ (1998b) http:\/\/yann.lecun.com\/exdb\/mnist\/"},{"key":"1454_CR32","doi-asserted-by":"publisher","unstructured":"Li X, Song Z, Yang J (2023) Federated adversarial learning: A framework with convergence analysis. In: Proceedings of the 40th International Conference on Machine Learning, https:\/\/doi.org\/10.48550\/arXiv.2208.03635","DOI":"10.48550\/arXiv.2208.03635"},{"key":"1454_CR33","doi-asserted-by":"publisher","unstructured":"Liu Z, Chen Y, Yu H, et al (2022) Gtg-shapley: efficient and accurate participant contribution evaluation in federated learning. ACM Trans Intell Syst Technol 13(4). https:\/\/doi.org\/10.1145\/3501811","DOI":"10.1145\/3501811"},{"key":"1454_CR34","doi-asserted-by":"publisher","unstructured":"Lundberg S, Lee SI (2017) A unified approach to interpreting model predictions. https:\/\/doi.org\/10.48550\/arXiv.1705.07874","DOI":"10.48550\/arXiv.1705.07874"},{"key":"1454_CR35","doi-asserted-by":"publisher","unstructured":"Luo X, Pei J (2024) Applications and computation of the shapley value in databases and machine learning. pp 630\u2013635, https:\/\/doi.org\/10.1145\/3626246.3654680","DOI":"10.1145\/3626246.3654680"},{"key":"1454_CR36","doi-asserted-by":"publisher","unstructured":"Ma M (2022) Application of an improved shapley value method in cooperative alliance game, pp 835\u2013840. https:\/\/doi.org\/10.1007\/978-3-031-05484-6_109","DOI":"10.1007\/978-3-031-05484-6_109"},{"key":"1454_CR37","unstructured":"Maleki S, Tran-Thanh L, Hines G, et al (2013) Bounding the Estimation Error of Sampling-based Shapley Value Approximation With\/Without Stratifying. ArXiv:1306.4265"},{"key":"1454_CR38","doi-asserted-by":"publisher","unstructured":"Mase M, Owen A, Seiler B (2019) Explaining black box decisions by shapley cohort refinement.https:\/\/doi.org\/10.48550\/arXiv.1911.00467","DOI":"10.48550\/arXiv.1911.00467"},{"key":"1454_CR39","unstructured":"McMahan H, Moore E, Ramage D, et al (2017) Communication-efficient learning of deep networks from decentralized data. ArXiv eprint 1610.02527. arXiv:1602.05629"},{"key":"1454_CR40","doi-asserted-by":"publisher","unstructured":"Mitchell R, Cooper J, Frank E, et al (2021) Sampling permutations for shapley value estimation. https:\/\/doi.org\/10.48550\/arXiv.2104.12199","DOI":"10.48550\/arXiv.2104.12199"},{"key":"1454_CR41","unstructured":"Mohammad R, McCluskey L (2015) https:\/\/archive.ics.uci.edu\/dataset\/327\/phishing+websites"},{"key":"1454_CR42","unstructured":"Mohammad R, Thabtah F, McCluskey T (2012) An assessment of features related to phishing websites using an automated technique. In: Proc. Intl. Conf. For Internet Technology And Secured Transactions. ICITST 2012, pp 492\u2013497"},{"key":"1454_CR43","doi-asserted-by":"publisher","first-page":"14388","DOI":"10.1609\/aaai.v38i13.29352","volume":"38","author":"M Muschalik","year":"2024","unstructured":"Muschalik M, Fumagalli F, Hammer B et al (2024) Beyond treeshap: efficient computation of any-order shapley interactions for tree ensembles. Proc AAAI Conf Artif Intell 38:14388\u201314396. https:\/\/doi.org\/10.1609\/aaai.v38i13.29352","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"1454_CR44","doi-asserted-by":"publisher","unstructured":"Musco C, Witter R (2024) Provably accurate shapley value estimation via leverage score sampling. https:\/\/doi.org\/10.48550\/arXiv.2410.01917","DOI":"10.48550\/arXiv.2410.01917"},{"key":"1454_CR45","doi-asserted-by":"publisher","unstructured":"Nagalapatti L, Narayanam R (2021) Game of Gradients: Mitigating Irrelevant Clients in Federated Learning. In: Proc. Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), pp 9046\u20139054, https:\/\/doi.org\/10.1609\/aaai.v35i10.17093","DOI":"10.1609\/aaai.v35i10.17093"},{"key":"1454_CR46","doi-asserted-by":"publisher","unstructured":"Okhrati R, Lipani A (2020) A multilinear sampling algorithm to estimate shapley values. https:\/\/doi.org\/10.48550\/arXiv.2010.12082","DOI":"10.48550\/arXiv.2010.12082"},{"key":"1454_CR47","doi-asserted-by":"publisher","unstructured":"Otmani K, El-Azouzi R, Labatut V (2024) Fedsv: Byzantine-robust federated learning via shapley value. In: ICC 2024 - IEEE International Conference on Communications, pp 4620\u20134625, https:\/\/doi.org\/10.1109\/ICC51166.2024.10622175","DOI":"10.1109\/ICC51166.2024.10622175"},{"key":"1454_CR48","unstructured":"Platt J (1998a) https:\/\/www.csie.ntu.edu.tw\/~cjlin\/libsvmtools\/datasets\/binary.html"},{"key":"1454_CR49","doi-asserted-by":"publisher","unstructured":"Platt J (1998b) Fast training of support vector machines using sequential minimal optimization. In: Schoelkopf B, Burges C, Smola A (eds) Advances in Kernel Methods - Support Vector Learning. MIT Press, https:\/\/doi.org\/10.7551\/mitpress\/1130.003.0016","DOI":"10.7551\/mitpress\/1130.003.0016"},{"key":"1454_CR50","unstructured":"Prokhorov D (2001) IJCNN 2001 Neural Network Competition, Ford Research Laboratory"},{"key":"1454_CR51","doi-asserted-by":"publisher","unstructured":"Rozemberczki B, Watson L, Bayer P, et al (2022) The shapley value in machine learning. In: The 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence, pp 5538\u20135545, https:\/\/doi.org\/10.24963\/ijcai.2022\/774","DOI":"10.24963\/ijcai.2022\/774"},{"key":"1454_CR52","doi-asserted-by":"publisher","unstructured":"Salarbashishahri M, Okegbile SD, Cai J (2022) A shapley value-enhanced evaluation technique for effective aggregation in federated learning. In: 2022 IEEE Future Networks World Forum (FNWF), pp 88\u201393, https:\/\/doi.org\/10.1109\/FNWF55208.2022.00024","DOI":"10.1109\/FNWF55208.2022.00024"},{"key":"1454_CR53","doi-asserted-by":"publisher","unstructured":"Shapley L (1953) A Value for N-person Games. In: Annals of Mathematical Studies: contributions to the Theory of Games, vol\u00a028. Princeton University Press, p 307-317, https:\/\/doi.org\/10.7249\/P0295","DOI":"10.7249\/P0295"},{"key":"1454_CR54","doi-asserted-by":"publisher","unstructured":"Song T, Tong Y, Wei S (2019) Profit Allocation for Federated Learning. In: Proc. 2019 IEEE International Conference on Big Data (Big Data), Los Angeles, CA, USA, https:\/\/doi.org\/10.1109\/BigData47090.2019.9006327","DOI":"10.1109\/BigData47090.2019.9006327"},{"key":"1454_CR55","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2021.102402","volume":"110","author":"N Truong","year":"2021","unstructured":"Truong N, Sun K, Wang S et al (2021) Privacy preservation in federated learning: an insightful survey from the gdpr perspective. Comput Secur 110:102402. https:\/\/doi.org\/10.1016\/j.cose.2021.102402","journal-title":"Comput Secur"},{"key":"1454_CR56","unstructured":"UCI Cardiotocography (2010) https:\/\/archive.ics.uci.edu\/dataset\/193\/cardiotocography"},{"key":"1454_CR57","unstructured":"UCI Pima Indians Diabetes (2008) https:\/\/www.kaggle.com\/datasets\/uciml\/pima-indians-diabetes-database"},{"key":"1454_CR58","unstructured":"UCI Retinopathy (2014) https:\/\/archive.ics.uci.edu\/dataset\/329\/ diabetic+retinopathy +debrecen"},{"key":"1454_CR59","doi-asserted-by":"crossref","unstructured":"Verhaeghe J, Van Der Donckt J, Ongenae F et al (2023) Powershap: a power-full shapley feature selection method. In: Canu S, Fischer A et al (eds) Amini MR. Databases. Springer International Publishing, Machine Learning and Knowledge Discovery in, pp 71\u201387","DOI":"10.1007\/978-3-031-26387-3_5"},{"key":"1454_CR60","doi-asserted-by":"crossref","unstructured":"Wang G, Dang C, Zhou Z (2019) Measure contribution of participants in federated learning. ArXiv:1909.08525","DOI":"10.1109\/BigData47090.2019.9006179"},{"key":"1454_CR61","first-page":"153","volume-title":"A principled approach to data valuation for federated learning","author":"T Wang","year":"2020","unstructured":"Wang T, Rausch J, Zhang C et al (2020) A principled approach to data valuation for federated learning. Privacy and Incentive, Federated Learning, pp 153\u2013167"},{"key":"1454_CR62","unstructured":"Watson L, Kujawa Z, Andreeva R, et al (2023) Accelerated shapley value approximation for data evaluation. arXiv:2311.05346"},{"key":"1454_CR63","unstructured":"Webb S, Caverlee J, et al (2006) Introducing the webb spam corpus: using email spam to identify web spam automatically. In: Proc. Third Conference on Email and Anti-Spam (CEAS)"},{"issue":"1\u20132","key":"1454_CR64","first-page":"28","volume":"34","author":"BL Welch","year":"1947","unstructured":"Welch BL (1947) The generalization of \u2018student\u2019s\u2019 problem when several different population variances are involved. Biometrika 34(1\u20132):28\u201335","journal-title":"Biometrika"},{"key":"1454_CR65","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2023.106305","volume":"159","author":"M Wu","year":"2023","unstructured":"Wu M, Jia R, Lin C et al (2023) Variance reduced shapley value estimation for trustworthy data valuation. Comput Oper Res 159:106305. https:\/\/doi.org\/10.1016\/j.cor.2023.106305","journal-title":"Comput Oper Res"},{"key":"1454_CR66","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TMC.2023.3316145","volume":"2","author":"A Xu","year":"2023","unstructured":"Xu A, Zheng Z, Li Q et al (2023) Vap: Online data valuation and pricing for machine learning models in mobile health. IEEE Trans Mobile Comput 2:1\u201317. https:\/\/doi.org\/10.1109\/TMC.2023.3316145","journal-title":"IEEE Trans Mobile Comput"},{"key":"1454_CR67","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/01621459.2023.2257364","volume":"119","author":"L Yang","year":"2023","unstructured":"Yang L, Zhou Y, Fu H et al (2023) Fast approximation of the shapley values based on order-of-addition experimental designs. J Am Stat Assoc 119:1\u201318. https:\/\/doi.org\/10.1080\/01621459.2023.2257364","journal-title":"J Am Stat Assoc"},{"key":"1454_CR68","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3339474","volume":"10","author":"Q Yang","year":"2019","unstructured":"Yang Q, Liu Y, Chen T et al (2019) Federated machine learning: concept and applications. ACM Trans Intell Syst Technol 10:1\u201319","journal-title":"ACM Trans Intell Syst Technol"},{"key":"1454_CR69","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/9690657","volume":"2022","author":"X Yang","year":"2022","unstructured":"Yang X, Tan W, Peng C et al (2022) Federated Learning Incentive Mechanism Design via Enhanced Shapley Value Method. Wirel Commun Mob Comput 2022:1\u201311. https:\/\/doi.org\/10.1155\/2022\/9690657","journal-title":"Wirel Commun Mob Comput"},{"key":"1454_CR70","doi-asserted-by":"publisher","unstructured":"Yongchan K, Zou J (2021) Beta shapley: a unified and noise-reduced data valuation framework for machine learning. https:\/\/doi.org\/10.48550\/arXiv.2110.14049","DOI":"10.48550\/arXiv.2110.14049"},{"key":"1454_CR71","doi-asserted-by":"publisher","first-page":"11245","DOI":"10.1609\/aaai.v37i9.26331","volume":"37","author":"J Zhang","year":"2023","unstructured":"Zhang J, Li B, Chen C et al (2023) Delving into the adversarial robustness of federated learning. Proc AAAI Conf Artif Intell 37:11245\u201311253. https:\/\/doi.org\/10.1609\/aaai.v37i9.26331","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"1454_CR72","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3588728","volume":"1","author":"J Zhang","year":"2023","unstructured":"Zhang J, Sun Q, Liu J et al (2023) Efficient sampling approaches to shapley value approximation. Proc ACM Manag Data 1:1\u201324. https:\/\/doi.org\/10.1145\/3588728","journal-title":"Proc ACM Manag Data"},{"key":"1454_CR73","doi-asserted-by":"publisher","unstructured":"Zhang J, Xia H, Sun Q, et al (2023c) Dynamic shapley value computation. pp 639\u2013652, https:\/\/doi.org\/10.1109\/ICDE55515.2023.0055","DOI":"10.1109\/ICDE55515.2023.0055"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-025-01454-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-025-01454-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-025-01454-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T16:39:23Z","timestamp":1751474363000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-025-01454-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,2]]},"references-count":73,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["1454"],"URL":"https:\/\/doi.org\/10.1007\/s10044-025-01454-5","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"type":"print","value":"1433-7541"},{"type":"electronic","value":"1433-755X"}],"subject":[],"published":{"date-parts":[[2025,4,2]]},"assertion":[{"value":"18 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This work is not subject to any Conflict of interest or Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest\/Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"77"}}