{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:11:40Z","timestamp":1780636300569,"version":"3.54.1"},"reference-count":137,"publisher":"Association for Computing Machinery (ACM)","issue":"6","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62472310, 62322208, 62232001, 12411530122, and 62472429"],"award-info":[{"award-number":["62472310, 62322208, 62232001, 12411530122, and 62472429"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001459","name":"Ministry of Education, Singapore","doi-asserted-by":"crossref","award":["MOET32020-0004"],"award-info":[{"award-number":["MOET32020-0004"]}],"id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2025,7,31]]},"abstract":"<jats:p>Deep learning (DL) systems have been widely utilized across various domains. However, the evolution of DL systems can result in regression faults. In addition to the evolution of DL systems through the incorporation of new data, feature evolution, such as the addition of new features, is also common and can introduce regression faults. In this work, we first investigate the underlying factors that are correlated with regression faults in feature evolution scenarios, i.e., redundancy and contribution shift. Based on our investigation, we propose a novel mitigation approach called FeaProtect, which aims to minimize the impact of these two factors. To evaluate the performance of FeaProtect, we conducted an extensive study comparing it with state-of-the-art approaches. The results show that FeaProtect outperforms the in-processing baseline approaches, with an average improvement of 50.6%\u201356.4% in terms of regression fault mitigation. We also show that FeaProtect can further enhance the effectiveness of mitigating regression faults by integrating with state-of-the-art post-processing approaches.<\/jats:p>","DOI":"10.1145\/3712199","type":"journal-article","created":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T17:07:44Z","timestamp":1736960864000},"page":"1-33","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Mitigating Regression Faults Induced by Feature Evolution in Deep Learning Systems"],"prefix":"10.1145","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2870-7801","authenticated-orcid":false,"given":"Hanmo","family":"You","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6173-8170","authenticated-orcid":false,"given":"Zan","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2417-4774","authenticated-orcid":false,"given":"Xuyang","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3056-9962","authenticated-orcid":false,"given":"Junjie","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3545-1392","authenticated-orcid":false,"given":"Jun","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8766-7235","authenticated-orcid":false,"given":"Shuang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0782-5044","authenticated-orcid":false,"given":"Zishuo","family":"Dong","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"Sparsh Gupta. 2024. Models: ANN for music genre classification. Retrieved from https:\/\/www.kaggle.com\/code\/imsparsh\/gtzan-genre-classification-deep-learning-val-92-4"},{"key":"e_1_3_2_3_2","unstructured":"SElab2019. 2024. Models: CNN for predictive mutation testing. Retrieved from https:\/\/github.com\/SElab2019\/ExtPMT"},{"key":"e_1_3_2_4_2","unstructured":"Youssef Elzahar. 2024. Models: FFNN for diabetes disease updated dataset. Retrieved from https:\/\/www.kaggle.com\/code\/youssefelzahar\/diabetes-disease"},{"key":"e_1_3_2_5_2","unstructured":"Ali Greo. 2024. Models: FFNN for dry beans classification. Retrieved from https:\/\/www.kaggle.com\/code\/aligreualihassan\/dry-beans-classification"},{"key":"e_1_3_2_6_2","unstructured":"Dewan Mahmuda Zaman. 2024. Models: FFNN for fetal health classification. Retrieved from https:\/\/www.kaggle.com\/code\/mahmudazaman\/dnn-multiclass-classification-93-accuracy"},{"key":"e_1_3_2_7_2","unstructured":"Oliveira and Henrique Silva. 2024. Models: FFNN for hand gesture prediction. Retrieved from https:\/\/www.kaggle.com\/code\/caldasdeoliveira\/hand-gesture-prediction-emg-dense-nn"},{"key":"e_1_3_2_8_2","unstructured":"Ahmed Ali Omar Haneen Hossam and Shady Nagy. 2024. Models: FFNN for mobile price prediction. Retrieved from https:\/\/www.kaggle.com\/code\/ahmedaliomar\/mobile-price-classification-neural-network-96-acc"},{"key":"e_1_3_2_9_2","unstructured":"Nanzhong-tju. 2024. Models: FFNN for patient treatment prediction. Retrieved from https:\/\/github.com\/nanzhong-tju\/DNN-model-for-patient-treatment-analysis"},{"key":"e_1_3_2_10_2","unstructured":"Pavan Kumar D. 2024. Models: FFNN for telco customer churn. Retrieved from https:\/\/www.kaggle.com\/code\/mragpavank\/predicting-customer-churn-for-a-telecom-company"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-69155-8_9"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3524842.3528490"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1002\/1520-6661(200009\/10)9:5<311::AID-MFM12>3.0.CO;2-9"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012429"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/72.298224"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1995.tb02031.x"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2010.11.028"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1038\/494155a"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICST.2013.21"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394112"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.3021387"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403341"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3569932"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","unstructured":"Lorenzo Ciampiconi Adam Elwood Marco Leonardi Ashraf Mohamed and Alessandro Rozza. 2023. A survey and taxonomy of loss functions in machine learning. arXiv:2301.05579. DOI: 10.48550\/arXiv.2301.05579","DOI":"10.48550\/arXiv.2301.05579"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.114.3.494"},{"key":"e_1_3_2_28_2","volume-title":"Tabular Data Synthesis Using Generative Adversarial Networks: An Application to Table Augmentation","author":"Couplet Edouard","year":"2021","unstructured":"Edouard Couplet, John Aldo Lee, and Michel Verleysen. 2021. Tabular Data Synthesis Using Generative Adversarial Networks: An Application to Table Augmentation. Master\u2019s thesis. UCLouvain."},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_30_2","unstructured":"Brian Dean. Accessed: 2024. Google\u2019s 200 ranking factors: The complete list. Retrieved from https:\/\/backlinko.com\/google-ranking-factors"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1080\/03610918.2020.1823413"},{"key":"e_1_3_2_32_2","series-title":"CEUR Workshop Proceedings, Vol. 2640","first-page":"134","volume-title":"AISafety@IJCAI","author":"Demir Samet","year":"2020","unstructured":"Samet Demir, Hasan Ferit Eniser, and Alper Sen. 2020. DeepSmartFuzzer: Reward guided Test generation for deep learning. In AISafety@IJCAI, CEUR Workshop Proceedings, Vol. 2640, CEUR-WS.org, 134\u2013140."},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","unstructured":"Huiqi Deng Na Zou Mengnan Du Weifu Chen Guocan Feng Ziwei Yang Zheyang Li and Quanshi Zhang. 2023. Understanding and unifying fourteen attribution methods with Taylor interactions. arXiv:2303.01506. DOI: 10.48550\/arXiv.2303.01506","DOI":"10.48550\/arXiv.2303.01506"},{"key":"e_1_3_2_34_2","first-page":"200144","article-title":"Chi \\({}^{2}\\) -MI: A hybrid feature selection based machine learning approach in diagnosis of chronic kidney disease","volume":"16","author":"Dey Samrat Kumar","year":"2022","unstructured":"Samrat Kumar Dey, Khandaker Mohammad Mohi Uddin, Hafiz Md. Hasan Babu, Md. Mahbubur Rahman, Arpita Howlader, and K. M. Aslam Uddin. 2022. Chi \\({}^{2}\\) -MI: A hybrid feature selection based machine learning approach in diagnosis of chronic kidney disease. Intell. Syst. Appl. 16 (2022), 200144.","journal-title":"Intell. Syst. Appl"},{"issue":"4","key":"e_1_3_2_35_2","first-page":"458","article-title":"Mobile phone price classification using machine learning","volume":"7","author":"Ercan Seda \u0130pek Aksoy","year":"2023","unstructured":"Seda \u0130pek Aksoy Ercan and Murat \u015e\u0130M\u015eEK. 2023. Mobile phone price classification using machine learning. Int. J. Adv. Nat. Sci. Eng. Res. 7, 4 (2023), 458\u2013462.","journal-title":"Int. J. Adv. Nat. Sci. Eng. Res"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00343-w"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3234629"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.2196\/12273"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.107865"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2917532"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0230164"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.172"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/SECON.2016.7506650"},{"key":"e_1_3_2_45_2","first-page":"19513","volume-title":"NeurIPS","author":"Hesse Robin","year":"2021","unstructured":"Robin Hesse, Simone Schaub-Meyer, and Stefan Roth. 2021. Fast axiomatic attribution for neural networks. In NeurIPS, 19513\u201319524."},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/8279342"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.3390\/e24070873"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3641848"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.3390\/computers8020042"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","unstructured":"Leonid Joffe. 2021. Transfer learning for tabular data. TechRxiv (2021). DOI: 10.36227\/techrxiv.16974124.v","DOI":"10.36227\/techrxiv.16974124.v"},{"key":"e_1_3_2_51_2","first-page":"29768","volume-title":"NeurIPS","author":"Karandikar Archit","year":"2021","unstructured":"Archit Karandikar, Nicholas Cain, Dustin Tran, Balaji Lakshminarayanan, Jonathon Shlens, Michael C. Mozer, and Becca Roelofs. 2021. Soft calibration objectives for neural networks. In NeurIPS, 29768\u201329779."},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.01.048"},{"key":"e_1_3_2_53_2","first-page":"372","volume-title":"SAI","author":"Khalid Samina","year":"2014","unstructured":"Samina Khalid, Tehmina Khalil, and Shamila Nasreen. 2014. A survey of feature selection and feature extraction techniques in machine learning. In SAI. IEEE, 372\u2013378."},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2023.24924"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2020.105507"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER.2015.7081843"},{"key":"e_1_3_2_57_2","unstructured":"Steven Levy. 2024. Exclusive: How Google\u2019s algorithm rules the web. Retrieved from https:\/\/www.wired.com\/2010\/02\/ff-google-algorithm\/"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijar.2018.10.004"},{"key":"e_1_3_2_59_2","first-page":"78","volume-title":"CIS","author":"Li Haidong","year":"2019","unstructured":"Haidong Li, Jiongcheng Li, Xiaoming Guan, Binghao Liang, Yuting Lai, and Xinglong Luo. 2019. Research on overfitting of deep learning. In CIS. IEEE, 78\u201381."},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3136625"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2017.8292668"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3290202"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00106"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-021-00699-w"},{"key":"e_1_3_2_65_2","first-page":"4765","volume-title":"NIPS","author":"Lundberg Scott M.","year":"2017","unstructured":"Scott M. Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. In NIPS, 4765\u20134774."},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/712"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICST.2019.00025"},{"key":"e_1_3_2_68_2","unstructured":"Alibaba Cloud MaxCompute. 2024. The power of AI: Why taobao knows online shoppers better Than they know themselves. Retrieved from https:\/\/tinyurl.com\/ailibaba"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.08.009"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534405"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13218-022-00766-6"},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICST.2011.60"},{"key":"e_1_3_2_73_2","first-page":"41:1","volume-title":"IDEAS","author":"Nassar Mohamed","year":"2019","unstructured":"Mohamed Nassar, Ha\u00efdar Safa, Alaa Al Mutawa, Ahmed Helal, and Iskander Gaba. 2019. Chi squared feature selection over Apache spark. In IDEAS. ACM, 41:1\u201341:5."},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3108802"},{"key":"e_1_3_2_75_2","series-title":"Proceedings of Machine Learning Research, Vol. 162","first-page":"16888","volume-title":"ICML","author":"Niu Shuaicheng","year":"2022","unstructured":"Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Yaofo Chen, Shijian Zheng, Peilin Zhao, and Mingkui Tan. 2022. Efficient test-time model adaptation without forgetting. In ICML, Proceedings of Machine Learning Research, Vol. 162, PMLR, 16888\u201316905."},{"key":"e_1_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3241537"},{"key":"e_1_3_2_77_2","volume-title":"The Design of Everyday Things: Revised and Expanded Edition","author":"Norman Don","year":"2013","unstructured":"Don Norman. 2013. The Design of Everyday Things: Revised and Expanded Edition. Basic books."},{"key":"e_1_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.3390\/app9235191"},{"key":"e_1_3_2_79_2","first-page":"1","volume-title":"Uncertainty & Robustness in Deep Learning Workshop","author":"Ortiz Jimenez Guillermo","year":"2020","unstructured":"Guillermo Ortiz Jimenez, Apostolos Modas, Seyed Mohsen Moosavi Dezfooli, and Pascal Frossard. 2020. Redundant features can hurt robustness to distributions shift. In Uncertainty & Robustness in Deep Learning Workshop. ICML, 1\u20138."},{"key":"e_1_3_2_80_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1073"},{"key":"e_1_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3106237.3122819"},{"key":"e_1_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.159"},{"key":"e_1_3_2_83_2","doi-asserted-by":"publisher","DOI":"10.1145\/3374214"},{"key":"e_1_3_2_84_2","doi-asserted-by":"publisher","DOI":"10.3390\/informatics7040049"},{"key":"e_1_3_2_85_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICTP48844.2019.9041736"},{"key":"e_1_3_2_86_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1205438"},{"key":"e_1_3_2_87_2","first-page":"1135","volume-title":"KDD","author":"Ribeiro Marco T\u00falio","year":"2016","unstructured":"Marco T\u00falio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. \u201cWhy should I trust you?\u201d: Explaining the predictions of any classifier. In KDD. ACM, 1135\u20131144."},{"key":"e_1_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10822-020-00314-0"},{"issue":"2","key":"e_1_3_2_89_2","first-page":"380","article-title":"Exploratory study of some machine learning techniques to classify the patient treatment","volume":"12","author":"Sadikin Mujiono","year":"2021","unstructured":"Mujiono Sadikin, Ida Nurhaida, and Ria Puspita Sari. 2021. Exploratory study of some machine learning techniques to classify the patient treatment. Int. J. Adv. Comput. Sci. Appl. 12, 2 (2021), 380\u2013387.","journal-title":"Int. J. Adv. Comput. Sci. Appl"},{"issue":"1","key":"e_1_3_2_90_2","first-page":"1","article-title":"Prediction model of wind Speed and direction using deep neural network","volume":"3","author":"Sari Anggraini Puspita","year":"2020","unstructured":"Anggraini Puspita Sari, Hiroshi Suzuki, Takahiro Kitajima, Takashi Yasuno, Dwi Arman Prasetya, and Nachrowie Nachrowie. 2020. Prediction model of wind Speed and direction using deep neural network. J. Electr. Eng. Mechatron. Comput. Sci. 3, 1 (2020), 1\u201310.","journal-title":"J. Electr. Eng. Mechatron. Comput. Sci"},{"key":"e_1_3_2_91_2","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1200"},{"key":"e_1_3_2_92_2","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"e_1_3_2_93_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-0793-4_5"},{"key":"e_1_3_2_94_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.02.016"},{"key":"e_1_3_2_95_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE.2019.00031"},{"key":"e_1_3_2_96_2","doi-asserted-by":"publisher","DOI":"10.1111\/epi.17733"},{"key":"e_1_3_2_97_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.11.011"},{"key":"e_1_3_2_98_2","doi-asserted-by":"publisher","DOI":"10.1145\/3563210"},{"key":"e_1_3_2_99_2","series-title":"CEUR Workshop Proceedings, Vol. 3215","first-page":"132","volume-title":"AISafety@IJCAI","author":"Tassi Cedrique Rovile Njieutcheu","year":"2022","unstructured":"Cedrique Rovile Njieutcheu Tassi, Jakob Gawlikowski, Auliya Unnisa Fitri, and Rudolph Triebel. 2022. The impact of averaging logits over probabilities on ensembles of neural networks. In AISafety@IJCAI, CEUR Workshop Proceedings, Vol. 3215, CEUR-WS.org, 132\u2013141."},{"key":"e_1_3_2_100_2","unstructured":"IBM Samples Team. 2024. Telco customer churn (11.1.3 \\(+\\) ). Retrieved from https:\/\/community.ibm.com\/community\/user\/businessanalytics\/blogs\/steven-macko\/2019\/07\/11\/telco-customer-churn-1113"},{"key":"e_1_3_2_101_2","unstructured":"Jillani Soft Tech. 2024. Diabetes disease updated dataset. Retrieved from https:\/\/www.kaggle.com\/datasets\/jillanisofttech\/diabetes-disease-updated-dataset"},{"key":"e_1_3_2_102_2","unstructured":"Greeg Titan and Elmajo Adriel. 2024. Climate data daily IDN. Retrieved from https:\/\/www.kaggle.com\/datasets\/greegtitan\/indonesia-climate"},{"key":"e_1_3_2_103_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER53432.2022.00128"},{"key":"e_1_3_2_104_2","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.14055"},{"key":"e_1_3_2_105_2","first-page":"116","volume-title":"NeurIPS","author":"Tr\u00e4uble Frederik","year":"2021","unstructured":"Frederik Tr\u00e4uble, Julius von K\u00fcgelgen, Matth\u00e4us Kleindessner, Francesco Locatello, Bernhard Sch\u00f6lkopf, and Peter V. Gehler. 2021. Backward-compatible prediction updates: A probabilistic approach. In NeurIPS, 116\u2013128."},{"key":"e_1_3_2_106_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.07.091"},{"key":"e_1_3_2_107_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"e_1_3_2_108_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2019.2949568"},{"key":"e_1_3_2_109_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhydrol.2022.128995"},{"key":"e_1_3_2_110_2","doi-asserted-by":"publisher","DOI":"10.1145\/3106237.3106258"},{"key":"e_1_3_2_111_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00046"},{"key":"e_1_3_2_112_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3282789"},{"key":"e_1_3_2_113_2","first-page":"171","volume-title":"Selected Tables in Mathematical Statistics","author":"Wilcoxon Frank","year":"1970","unstructured":"Frank Wilcoxon, S. K. Katti, and Roberta A. Wilcox. 1970. Critical values and probability levels for the Wilcoxon rank sum test and the Wilcoxon signed rank test. In Selected Tables in Mathematical Statistics. Vol. 1, 171\u2013259."},{"key":"e_1_3_2_114_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2022.119505"},{"key":"e_1_3_2_115_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ces.2023.118619"},{"key":"e_1_3_2_116_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01620"},{"key":"e_1_3_2_117_2","doi-asserted-by":"publisher","DOI":"10.1145\/3293882.3330579"},{"key":"e_1_3_2_118_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.515"},{"key":"e_1_3_2_119_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2017.2766884"},{"key":"e_1_3_2_120_2","first-page":"7333","volume-title":"NeurIPS","author":"Xu Lei","year":"2019","unstructured":"Lei Xu, Maria Skoularidou, Alfredo Cuesta-Infante, and Kalyan Veeramachaneni. 2019. Modeling tabular data using conditional GAN. In NeurIPS, 7333\u20137343."},{"key":"e_1_3_2_121_2","doi-asserted-by":"publisher","unstructured":"Lei Xu and Kalyan Veeramachaneni. 2018. Synthesizing tabular data using generative adversarial networks. arXiv:1811.11264. DOI: 10.48550\/arXiv.1811.11264","DOI":"10.48550\/arXiv.1811.11264"},{"key":"e_1_3_2_122_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-017-1131-4"},{"key":"e_1_3_2_123_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01407"},{"key":"e_1_3_2_124_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2021.12.028"},{"key":"e_1_3_2_125_2","unstructured":"Kirill Yashuk. 2024. Classify gestures by reading muscle activity. Retrieved from https:\/\/www.kaggle.com\/datasets\/kyr7plus\/emg-4"},{"key":"e_1_3_2_126_2","doi-asserted-by":"publisher","DOI":"10.1002\/stv.430"},{"key":"e_1_3_2_127_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00019"},{"key":"e_1_3_2_128_2","first-page":"639","volume-title":"BIBM","author":"Yu Jun","year":"2022","unstructured":"Jun Yu, Benjamin Zalatan, Yong Chen, Li Shen, and Lifang He. 2022. Tensor-based multi-modal multi-target regression for Alzheimer\u2019s disease prediction. In BIBM. IEEE, 639\u2013646."},{"key":"e_1_3_2_129_2","doi-asserted-by":"publisher","DOI":"10.1145\/2351676.2351681"},{"key":"e_1_3_2_130_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3054008"},{"key":"e_1_3_2_131_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2018.2809496"},{"key":"e_1_3_2_132_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2019.2962027"},{"key":"e_1_3_2_133_2","first-page":"1","article-title":"AdaptCL: Adaptive Continual Learning for Tackling Heterogeneity in Sequential Datasets","author":"Zhao Yuqing","year":"2023","unstructured":"Yuqing Zhao, Divya Saxena, and Jiannong Cao. 2023. AdaptCL: Adaptive Continual Learning for Tackling Heterogeneity in Sequential Datasets. IEEE Trans. Neural Netw. Learn. Syst. (2023), 1\u201314.","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"e_1_3_2_134_2","doi-asserted-by":"publisher","DOI":"10.5555\/2898607.2898716"},{"key":"e_1_3_2_135_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219826"},{"key":"e_1_3_2_136_2","first-page":"2169","volume-title":"CCS","author":"Zhu Xiaogang","year":"2021","unstructured":"Xiaogang Zhu and Marcel B\u00f6hme. 2021. Regression greybox fuzzing. In CCS. ACM, 2169\u20132182."},{"issue":"7","key":"e_1_3_2_137_2","first-page":"2056","article-title":"Survey on testing of intelligent systems in autonomous vehicles","volume":"32","author":"Zhu Xianglei","year":"2021","unstructured":"Xianglei Zhu, Haichi Wang, Hanmo You, Weiheng Zhang, Yingyi Zhang, Shuang Liu, Junjie Chen, Zan Wang, and Keqiu Li. 2021. Survey on testing of intelligent systems in autonomous vehicles. J. Softw. 32, 7 (2021), 2056\u20132077.","journal-title":"J. Softw"},{"key":"e_1_3_2_138_2","unstructured":"Martin Zinkevich. 2017. Rules of machine learning: Best practices for ML engineering. Retrieved from https:\/\/developers.google.com\/machine-learning\/guides\/rules-of-ml"}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712199","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T13:31:04Z","timestamp":1751376664000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712199"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":137,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,7,31]]}},"alternative-id":["10.1145\/3712199"],"URL":"https:\/\/doi.org\/10.1145\/3712199","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]},"assertion":[{"value":"2024-06-26","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}