{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T22:54:57Z","timestamp":1754261697572},"reference-count":66,"publisher":"Association for Computing Machinery (ACM)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2021,11]]},"abstract":"<jats:p>How can we debug a logistic regression model in a federated learning setting when seeing the model behave unexpectedly (e.g., the model rejects all high-income customers' loan applications)? The SQL-based training data debugging framework has proved effective to fix this kind of issue in a non-federated learning setting. Given an unexpected query result over model predictions, this framework automatically removes the label errors from training data such that the unexpected behavior disappears in the retrained model. In this paper, we enable this powerful framework for federated learning. The key challenge is how to develop a security protocol for federated debugging which is proved to be secure, efficient, and accurate. Achieving this goal requires us to investigate how to seamlessly integrate the techniques from multiple fields (Databases, Machine Learning, and Cybersecurity). We first propose FedRain, which extends Rain, the state-of-the-art SQL-based training data debugging framework, to our federated learning setting. We address several technical challenges to make FedRain work and analyze its security guarantee and time complexity. The analysis results show that FedRain falls short in terms of both efficiency and security. To overcome these limitations, we redesign our security protocol and propose Frog, a novel SQL-based training data debugging framework tailored for federated learning. Our theoretical analysis shows that Frog is more secure, more accurate, and more efficient than FedRain. We conduct extensive experiments using several real-world datasets and a case study. The experimental results are consistent with our theoretical analysis and validate the effectiveness of Frog in practice.<\/jats:p>","DOI":"10.14778\/3494124.3494125","type":"journal-article","created":{"date-parts":[[2022,2,5]],"date-time":"2022-02-05T00:31:46Z","timestamp":1644021106000},"page":"388-400","source":"Crossref","is-referenced-by-count":9,"title":["Enabling SQL-based training data debugging for federated learning"],"prefix":"10.14778","volume":"15","author":[{"given":"Yejia","family":"Liu","sequence":"first","affiliation":[{"name":"Simon Fraser University, Burnaby, BC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiyuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Burnaby, BC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lampros","family":"Flokas","sequence":"additional","affiliation":[{"name":"Columbia University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiannan","family":"Wang","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Burnaby, BC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eugene","family":"Wu","sequence":"additional","affiliation":[{"name":"Columbia University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,2,4]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"2018 reform of eu data protection rules. https:\/\/ec.europa.eu\/info\/sites\/default\/files\/data-protection-factsheet-changes_en.pdf. Accessed: 2021-10-23.  2018 reform of eu data protection rules. https:\/\/ec.europa.eu\/info\/sites\/default\/files\/data-protection-factsheet-changes_en.pdf. Accessed: 2021-10-23."},{"key":"e_1_2_1_2_1","unstructured":"An Industrial Grade Federated Learning Framework. https:\/\/www.fedai.org. Accessed: 2021-05-31.  An Industrial Grade Federated Learning Framework. https:\/\/www.fedai.org. Accessed: 2021-05-31."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.14778\/3297753.3297761"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.21552\/EDPL\/2016\/3\/4"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1989284.1989302"},{"key":"e_1_2_1_6_1","volume-title":"Automated data validation in machine learning systems","author":"Biessmann F.","year":"2021","unstructured":"F. Biessmann , J. R. Golebiowski , T. Rukat , D. Lange , and P. Schmidt . Automated data validation in machine learning systems . 2021 . F. Biessmann, J. R. Golebiowski, T. Rukat, D. Lange, and P. Schmidt. Automated data validation in machine learning systems. 2021."},{"key":"e_1_2_1_7_1","volume-title":"Proceedings of SysML","author":"Breck E.","year":"2019","unstructured":"E. Breck , M. Zinkevich , N. Polyzotis , S. Whang , and S. Roy . Data validation for machine learning . In Proceedings of SysML , 2019 . E. Breck, M. Zinkevich, N. Polyzotis, S. Whang, and S. Roy. Data validation for machine learning. In Proceedings of SysML, 2019."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2018.01.007"},{"key":"e_1_2_1_9_1","volume-title":"The California Consumer Privacy Act (CCPA): An implementation guide","author":"P.","year":"2019","unstructured":"P. BUKATY. The California Consumer Privacy Act (CCPA): An implementation guide . IT Governance Publishing , 2019 . P. BUKATY. The California Consumer Privacy Act (CCPA): An implementation guide. IT Governance Publishing, 2019."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134061"},{"key":"e_1_2_1_11_1","volume-title":"FOCUS: dealing with label quality disparity in federated learning. CoRR, abs\/2001.11359","author":"Chen Y.","year":"2020","unstructured":"Y. Chen , X. Yang , X. Qin , H. Yu , B. Chen , and Z. Shen . FOCUS: dealing with label quality disparity in federated learning. CoRR, abs\/2001.11359 , 2020 . Y. Chen, X. Yang, X. Qin, H. Yu, B. Chen, and Z. Shen. FOCUS: dealing with label quality disparity in federated learning. CoRR, abs\/2001.11359, 2020."},{"key":"e_1_2_1_12_1","volume-title":"Secureboost: A lossless federated learning framework. CoRR, abs\/1901.08755","author":"Cheng K.","year":"2019","unstructured":"K. Cheng , T. Fan , Y. Jin , Y. Liu , T. Chen , and Q. Yang . Secureboost: A lossless federated learning framework. CoRR, abs\/1901.08755 , 2019 . K. Cheng, T. Fan, Y. Jin, Y. Liu, T. Chen, and Q. Yang. Secureboost: A lossless federated learning framework. CoRR, abs\/1901.08755, 2019."},{"key":"e_1_2_1_13_1","volume-title":"Python paillier library. https:\/\/github.com\/data61\/python-paillier","year":"2013","unstructured":"CSIRO's Data61. Python paillier library. https:\/\/github.com\/data61\/python-paillier , 2013 . CSIRO's Data61. Python paillier library. https:\/\/github.com\/data61\/python-paillier, 2013."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972740.21"},{"key":"e_1_2_1_15_1","volume-title":"UCI machine learning repository","author":"Dua D.","year":"2017","unstructured":"D. Dua and C. Graff . UCI machine learning repository , 2017 . D. Dua and C. Graff. UCI machine learning repository, 2017."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1214\/009053604000000067"},{"key":"e_1_2_1_17_1","volume-title":"Automated machine learning: State-of-the-art and open challenges","author":"Elshawi R.","year":"2019","unstructured":"R. Elshawi , M. Maher , and S. Sakr . Automated machine learning: State-of-the-art and open challenges , 2019 . R. Elshawi, M. Maher, and S. Sakr. Automated machine learning: State-of-the-art and open challenges, 2019."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/2911024"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1265530.1265535"},{"key":"e_1_2_1_20_1","volume-title":"Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption. CoRR, abs\/1711.10677","author":"Hardy S.","year":"2017","unstructured":"S. Hardy , W. Henecka , H. Ivey-Law , R. Nock , G. Patrini , G. Smith , and B. Thorne . Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption. CoRR, abs\/1711.10677 , 2017 . S. Hardy, W. Henecka, H. Ivey-Law, R. Nock, G. Patrini, G. Smith, and B. Thorne. Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption. CoRR, abs\/1711.10677, 2017."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3319888"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/579525"},{"key":"e_1_2_1_23_1","volume-title":"June","author":"Horsen C. V.","year":"2016","unstructured":"C. V. Horsen . gmpy2 2.0.8. https:\/\/pypi.org\/project\/gmpy2\/ , June 2016 . C. V. Horsen. gmpy2 2.0.8. https:\/\/pypi.org\/project\/gmpy2\/, June 2016."},{"key":"e_1_2_1_24_1","volume-title":"Privacy-preserving decentralized aggregation for federated learning. CoRR, abs\/2012.07183","author":"Jeon B.","year":"2020","unstructured":"B. Jeon , S. M. Ferdous , M. R. Rahman , and A. Walid . Privacy-preserving decentralized aggregation for federated learning. CoRR, abs\/2012.07183 , 2020 . B. Jeon, S. M. Ferdous, M. R. Rahman, and A. Walid. Privacy-preserving decentralized aggregation for federated learning. CoRR, abs\/2012.07183, 2020."},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-011-0463-8"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989411"},{"key":"e_1_2_1_27_1","first-page":"2020","article-title":"Model assertions for monitoring and improving ML models. In I. S. Dhillon, D. S. Papailiopoulos, and V. Sze, editors, MLSys 2020, Austin","author":"Kang D.","year":"2020","unstructured":"D. Kang , D. Raghavan , P. Bailis , and M. Zaharia . Model assertions for monitoring and improving ML models. In I. S. Dhillon, D. S. Papailiopoulos, and V. Sze, editors, MLSys 2020, Austin , TX, USA, March 2--4 , 2020 . mlsys.org, 2020 . D. Kang, D. Raghavan, P. Bailis, and M. Zaharia. Model assertions for monitoring and improving ML models. In I. S. Dhillon, D. S. Papailiopoulos, and V. Sze, editors, MLSys 2020, Austin, TX, USA, March 2--4, 2020. mlsys.org, 2020.","journal-title":"TX, USA, March 2--4"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57321-8_29"},{"key":"e_1_2_1_29_1","volume-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings","author":"Kingma D. P.","year":"2015","unstructured":"D. P. Kingma and J. Ba . Adam: A method for stochastic optimization. In Y. Bengio and Y. LeCun, editors , 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings , 2015 . D. P. Kingma and J. Ba. Adam: A method for stochastic optimization. In Y. Bengio and Y. LeCun, editors, 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings, 2015."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305576"},{"key":"e_1_2_1_31_1","volume-title":"Boostclean: Automated error detection and repair for machine learning. CoRR, abs\/1711.01299","author":"Krishnan S.","year":"2017","unstructured":"S. Krishnan , M. J. Franklin , K. Goldberg , and E. Wu . Boostclean: Automated error detection and repair for machine learning. CoRR, abs\/1711.01299 , 2017 . S. Krishnan, M. J. Franklin, K. Goldberg, and E. Wu. Boostclean: Automated error detection and repair for machine learning. CoRR, abs\/1711.01299, 2017."},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994514"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5895"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2020.2988525"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3324956"},{"key":"e_1_2_1_36_1","volume-title":"Federated learning: Collaborative machine learning without centralized training data","author":"McMahan B.","year":"2013","unstructured":"B. McMahan and D. Ramage . Federated learning: Collaborative machine learning without centralized training data , 2013 . B. McMahan and D. Ramage. Federated learning: Collaborative machine learning without centralized training data, 2013."},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3457607"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.14778\/2733004.2733070"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213875"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.10.007"},{"key":"e_1_2_1_41_1","volume-title":"From cleaning before ml to cleaning for ml. Data Engineering, page 24","author":"Neutatz F.","year":"2021","unstructured":"F. Neutatz , B. Chen , Z. Abedjan , and E. Wu . From cleaning before ml to cleaning for ml. Data Engineering, page 24 , 2021 . F. Neutatz, B. Chen, Z. Abedjan, and E. Wu. From cleaning before ml to cleaning for ml. Data Engineering, page 24, 2021."},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/1756123.1756146"},{"key":"e_1_2_1_43_1","volume-title":"Quality inference in federated learning with secure aggregation","author":"Pej\u00f3 B.","year":"2021","unstructured":"B. Pej\u00f3 and G. Bicz\u00f3k . Quality inference in federated learning with secure aggregation , 2021 . B. Pej\u00f3 and G. Bicz\u00f3k. Quality inference in federated learning with secure aggregation, 2021."},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3154794"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3054782"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137631"},{"key":"e_1_2_1_47_1","volume-title":"A data quality-driven view of mlops. ArXiv, abs\/2102.07750","author":"Renggli C.","year":"2021","unstructured":"C. Renggli , L. Rimanic , N. M. Gurel , B. Karlavs , W. Wu , and C. Zhang . A data quality-driven view of mlops. ArXiv, abs\/2102.07750 , 2021 . C. Renggli, L. Rimanic, N. M. Gurel, B. Karlavs, W. Wu, and C. Zhang. A data quality-driven view of mlops. ArXiv, abs\/2102.07750, 2021."},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.14778\/2856318.2856329"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2588578"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445518"},{"key":"e_1_2_1_51_1","unstructured":"J. R. Shewchuk. An introduction to the conjugate gradient method without the agonizing pain. August 1994.  J. R. Shewchuk. An introduction to the conjugate gradient method without the agonizing pain. August 1994."},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006327"},{"key":"e_1_2_1_53_1","volume-title":"Towards federated graph learning for collaborative financial crimes detection","author":"Suzumura T.","year":"2019","unstructured":"T. Suzumura , Y. Zhou , N. Baracaldo , G. Ye , K. Houck , R. Kawahara , A. Anwar , L. L. Stavarache , Y. Watanabe , P. Loyola , D. Klyashtorny , H. Ludwig , and K. Bhaskaran . Towards federated graph learning for collaborative financial crimes detection , 2019 . T. Suzumura, Y. Zhou, N. Baracaldo, G. Ye, K. Houck, R. Kawahara, A. Anwar, L. L. Stavarache, Y. Watanabe, P. Loyola, D. Klyashtorny, H. Ludwig, and K. Bhaskaran. Towards federated graph learning for collaborative financial crimes detection, 2019."},{"key":"e_1_2_1_54_1","volume-title":"Federboost: Private federated learning for GBDT. CoRR, abs\/2011.02796","author":"Tian Z.","year":"2020","unstructured":"Z. Tian , R. Zhang , X. Hou , J. Liu , and K. Ren . Federboost: Private federated learning for GBDT. CoRR, abs\/2011.02796 , 2020 . Z. Tian, R. Zhang, X. Hou, J. Liu, and K. Ren. Federboost: Private federated learning for GBDT. CoRR, abs\/2011.02796, 2020."},{"key":"e_1_2_1_55_1","series-title":"Proceedings of Machine Learning Research","first-page":"6618","volume-title":"Proceedings of the 36th International Conference on Machine Learning, ICML","author":"Wang H.","year":"2019","unstructured":"H. Wang , B. Ustun , and F. P. Calmon . Repairing without retraining: Avoiding disparate impact with counterfactual distributions . In K. Chaudhuri and R. Salakhutdinov, editors, Proceedings of the 36th International Conference on Machine Learning, ICML 2019 , 9--15 June 2019, Long Beach, California, USA , volume 97 of Proceedings of Machine Learning Research , pages 6618 -- 6627 . PMLR , 2019. H. Wang, B. Ustun, and F. P. Calmon. Repairing without retraining: Avoiding disparate impact with counterfactual distributions. In K. Chaudhuri and R. Salakhutdinov, editors, Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9--15 June 2019, Long Beach, California, USA, volume 97 of Proceedings of Machine Learning Research, pages 6618--6627. PMLR, 2019."},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824117"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536354.2536356"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389696"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.14778\/3407790.3407811"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3380568"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"e_1_2_1_62_1","volume-title":"Federated Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning","author":"Yang Q.","year":"2019","unstructured":"Q. Yang , Y. Liu , Y. Cheng , Y. Kang , T. Chen , and H. Yu . Federated Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning . Morgan & Claypool Publishers , 2019 . Q. Yang, Y. Liu, Y. Cheng, Y. Kang, T. Chen, and H. Yu. Federated Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan & Claypool Publishers, 2019."},{"key":"e_1_2_1_63_1","volume-title":"Parallel distributed logistic regression for vertical federated learning without third-party coordinator. CoRR, abs\/1911.09824","author":"Yang S.","year":"2019","unstructured":"S. Yang , B. Ren , X. Zhou , and L. Liu . Parallel distributed logistic regression for vertical federated learning without third-party coordinator. CoRR, abs\/1911.09824 , 2019 . S. Yang, B. Ren, X. Zhou, and L. Liu. Parallel distributed logistic regression for vertical federated learning without third-party coordinator. CoRR, abs\/1911.09824, 2019."},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-23551-2_2"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.5555\/3042817.3042973"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278779"}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3494124.3494125","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T11:24:40Z","timestamp":1672226680000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3494124.3494125"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11]]},"references-count":66,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,11]]}},"alternative-id":["10.14778\/3494124.3494125"],"URL":"https:\/\/doi.org\/10.14778\/3494124.3494125","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2021,11]]}}}