{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:44:07Z","timestamp":1787017447702,"version":"build-2736575974"},"reference-count":64,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T00:00:00Z","timestamp":1685059200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Singapore Ministry of Education Academic Research Fund Tier 3","award":["MOE2017-T3-1-007"],"award-info":[{"award-number":["MOE2017-T3-1-007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Manag. Data"],"published-print":{"date-parts":[[2023,5,26]]},"abstract":"<jats:p>In line with the increasing machine learning model inference accuracy, deep learning (DL) models have been increasingly applied to structured data for a wide spectrum of real-world applications, including product recommendations, online advertisement, healthcare analytics and risk analysis. However, unlike unstructured data, structured data is high-dimensional and sparse and therefore engenders a large number of parameters in DL, making DL models more prone to overfitting. To alleviate the overfitting problem, various regularization methods have been designed to constrain the model parameters as a means to control the model complexity. Unfortunately, these methods are often restricted to regularizing the parameter values directly without considering the intrinsic correlations and dependencies between attribute fields of structured data which is however key to effective structured data modeling.<\/jats:p>\n                  <jats:p>In this paper, we re-examine DL for structured data from a new perspective of attribute interactions. In particular, we seek to explicitly model and regularize the pairwise relationships between attribute fields of structured data, in a field-adaptive manner, via a proposed attentive and interpretable framework called ATT-Reg. Specifically, in this framework, a set of attentive weight matrices are introduced to each attribute field for modeling obviously different relationships with its neighboring attribute fields. Further, we derive from the Bayesian viewpoint a novel Attentive Regularization method for imposing adaptive regularization strengths on different pairs of attribute fields, based on the informativeness of their relationship, which is calculated using both data-driven information and functional dependency (FD) knowledge. Such adaptive regularization facilitates each attribute field to learn discriminative and diversified representations for more effective predictive analytics. We also develop a feature attribution method for supporting more interpretable predictions We validate the effectiveness of our ATT-Reg on six real-world datasets. Extensive experimental results show that ATT-Reg achieves significant improvement over state-of-the-art graph models, attentive models as well as regularization methods and supports an excellent degree of interpretation.<\/jats:p>","DOI":"10.1145\/3588936","type":"journal-article","created":{"date-parts":[[2023,5,30]],"date-time":"2023-05-30T13:42:05Z","timestamp":1685454125000},"page":"1-27","source":"Crossref","is-referenced-by-count":13,"title":["Regularized Pairwise Relationship based Analytics for Structured Data"],"prefix":"10.1145","volume":"1","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7271-3999","authenticated-orcid":false,"given":"Zhaojing","family":"Luo","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8605-076X","authenticated-orcid":false,"given":"Shaofeng","family":"Cai","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9887-5224","authenticated-orcid":false,"given":"Yatong","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4446-1100","authenticated-orcid":false,"given":"Beng Chin","family":"Ooi","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,5,30]]},"reference":[{"key":"e_1_2_2_1_1","volume-title":"Pattern recognition and machine learning","author":"Anzai Yuichiro","unstructured":"Yuichiro Anzai. 2012. Pattern recognition and machine learning. Elsevier."},{"key":"e_1_2_2_2_1","volume-title":"Automatic discovery of functional dependencies and conditional functional dependencies: a comparative study. university of Waterloo","author":"Asghar Nabiha","year":"2015","unstructured":"Nabiha Asghar and Amira Ghenai. 2015. Automatic discovery of functional dependencies and conditional functional dependencies: a comparative study. university of Waterloo (2015)."},{"key":"e_1_2_2_3_1","volume-title":"IJCAI-17 workshop on explainable AI","volume":"8","author":"Biran Or","year":"2017","unstructured":"Or Biran and Courtenay Cotton. 2017. Explanation and justification in machine learning: A survey. In IJCAI-17 workshop on explainable AI, Vol. 8. 8--13."},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3076246.3076251"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.14778\/3364324.3364325"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457321"},{"key":"e_1_2_2_7_1","volume-title":"Logic-based approach to semantic query optimization. ACM Transactions on Database Systems","author":"Chakravarthy Upen S","year":"1990","unstructured":"Upen S Chakravarthy, John Grant, and Jack Minker. 1990. Logic-based approach to semantic query optimization. ACM Transactions on Database Systems (1990), 162--207."},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137633"},{"key":"e_1_2_2_9_1","first-page":"13773","article-title":"Understanding gradient clipping in private SGD: A geometric perspective","volume":"33","author":"Chen Xiangyi","year":"2020","unstructured":"Xiangyi Chen, Steven Z Wu, and Mingyi Hong. 2020. Understanding gradient clipping in private SGD: A geometric perspective. Advances in Neural Information Processing Systems, Vol. 33 (2020), 13773--13782.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5768"},{"key":"e_1_2_2_11_1","volume-title":"Reducing overfitting in deep networks by decorrelating representations. arXiv preprint arXiv:1511.06068","author":"Cogswell Michael","year":"2015","unstructured":"Michael Cogswell, Faruk Ahmed, Ross Girshick, Larry Zitnick, and Dhruv Batra. 2015. Reducing overfitting in deep networks by decorrelating representations. arXiv preprint arXiv:1511.06068 (2015)."},{"key":"e_1_2_2_12_1","volume-title":"Overfitting and undercomputing in machine learning. ACM computing surveys","author":"Dietterich Tom","year":"1995","unstructured":"Tom Dietterich. 1995. Overfitting and undercomputing in machine learning. ACM computing surveys (1995), 326--327."},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3324957"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467228"},{"key":"e_1_2_2_15_1","volume-title":"Conditional functional dependencies for capturing data inconsistencies. ACM Transactions on Database Systems","author":"Fan Wenfei","year":"2008","unstructured":"Wenfei Fan, Floris Geerts, Xibei Jia, and Anastasios Kementsietsidis. 2008. Conditional functional dependencies for capturing data inconsistencies. ACM Transactions on Database Systems (2008), 1--48."},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3332281"},{"key":"e_1_2_2_17_1","volume-title":"A survey of methods for explaining black box models. ACM computing surveys","author":"Guidotti Riccardo","year":"2018","unstructured":"Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Franco Turini, Fosca Giannotti, and Dino Pedreschi. 2018. A survey of methods for explaining black box models. ACM computing surveys, Vol. 51, 5 (2018), 1--42."},{"key":"e_1_2_2_18_1","volume-title":"The movielens datasets: History and context. Acm transactions on interactive intelligent systems","author":"Maxwell Harper F","year":"2015","unstructured":"F Maxwell Harper and Joseph A Konstan. 2015. The movielens datasets: History and context. Acm transactions on interactive intelligent systems, Vol. 5, 4 (2015), 1--19."},{"key":"e_1_2_2_19_1","volume-title":"Proceedings 14th International Conference on Data Engineering. 392--401","author":"Huhtala Y.","unstructured":"Y. Huhtala, J. Karkkainen, P. Porkka, and H. Toivonen. 1998. Efficient discovery of functional and approximate dependencies using partitions. In Proceedings 14th International Conference on Data Engineering. 392--401."},{"key":"e_1_2_2_20_1","volume-title":"TANE: An efficient algorithm for discovering functional and approximate dependencies. The computer journal","author":"Huhtala Yka","year":"1999","unstructured":"Yka Huhtala, Juha K\"arkk\"ainen, Pasi Porkka, and Hannu Toivonen. 1999. TANE: An efficient algorithm for discovering functional and approximate dependencies. The computer journal (1999), 100--111."},{"key":"e_1_2_2_21_1","volume-title":"Learning models over relational data using sparse tensors and functional dependencies. ACM Transactions on Database Systems","author":"Khamis Mahmoud Abo","year":"2020","unstructured":"Mahmoud Abo Khamis, Hung Q Ngo, XuanLong Nguyen, Dan Olteanu, and Maximilian Schleich. 2020. Learning models over relational data using sparse tensors and functional dependencies. ACM Transactions on Database Systems (2020), 1--66."},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3320218"},{"key":"e_1_2_2_23_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9876.2010.00723.x"},{"key":"e_1_2_2_25_1","volume-title":"Proceedings of ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 202--207","author":"Ron","unstructured":"Ron Kohavi et al. 1996. Scaling up the accuracy of naive-bayes classifiers: A decision-tree hybrid. In Proceedings of ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 202--207."},{"key":"e_1_2_2_26_1","volume-title":"Hertz","author":"Krogh Anders","year":"1991","unstructured":"Anders Krogh and John A. Hertz. 1991. A Simple Weight Decay Can Improve Generalization. In Advances in Neural Information Processing Systems. 950--957."},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2882952"},{"key":"e_1_2_2_28_1","volume-title":"Practical large-scale optimization for max-norm regularization. Advances in neural information processing systems","author":"Lee Jason D","year":"2010","unstructured":"Jason D Lee, Ben Recht, Nathan Srebro, Joel Tropp, and Russ R Salakhutdinov. 2010. Practical large-scale optimization for max-norm regularization. Advances in neural information processing systems, Vol. 23 (2010)."},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352129"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3319878"},{"key":"e_1_2_2_31_1","volume-title":"A unified approach to interpreting model predictions. Advances in neural information processing systems","author":"Lundberg Scott M","year":"2017","unstructured":"Scott M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2916683"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17067"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2018.00051"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00146"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1214\/009053606000000281"},{"key":"e_1_2_2_37_1","volume-title":"Explanation in artificial intelligence: Insights from the social sciences. Artificial intelligence","author":"Miller Tim","year":"2019","unstructured":"Tim Miller. 2019. Explanation in artificial intelligence: Insights from the social sciences. Artificial intelligence, Vol. 267 (2019), 1--38."},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2014.03.001"},{"key":"e_1_2_2_39_1","unstructured":"Sergio Moro Raul Laureano and Paulo Cortez. 2011. Using data mining for bank direct marketing: An application of the crisp-dm methodology. (2011)."},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3384702"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.14778\/2794367.2794377"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.1996.492110"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467216"},{"key":"e_1_2_2_44_1","volume-title":"Database management systems","author":"Ramakrishnan Raghu","unstructured":"Raghu Ramakrishnan, Johannes Gehrke, and Johannes Gehrke. 2003. Database management systems. Vol. 3. McGraw-Hill New York."},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137631"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.14778\/2535573.2488340"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"e_1_2_2_48_1","volume-title":"European semantic web conference","author":"Schlichtkrull Michael","unstructured":"Michael Schlichtkrull, Thomas N Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, and Max Welling. 2018. Modeling relational data with graph convolutional networks. In European semantic web conference. Springer, 593--607."},{"key":"e_1_2_2_49_1","volume-title":"Saint: Improved neural networks for tabular data via row attention and contrastive pre-training. arXiv preprint arXiv:2106.01342","author":"Somepalli Gowthami","year":"2021","unstructured":"Gowthami Somepalli, Micah Goldblum, Avi Schwarzschild, C Bayan Bruss, and Tom Goldstein. 2021. Saint: Improved neural networks for tabular data via row attention and contrastive pre-training. arXiv preprint arXiv:2106.01342 (2021)."},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357925"},{"key":"e_1_2_2_51_1","unstructured":"Nathan Srebro Jason Rennie and Tommi S Jaakkola. 2005. Maximum-margin matrix factorization. In Advances in neural information processing systems. 1329--1336."},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/11503415_37"},{"key":"e_1_2_2_53_1","volume-title":"Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research","author":"Srivastava Nitish","year":"2014","unstructured":"Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, Vol. 15, 1 (2014), 1929--1958."},{"key":"e_1_2_2_54_1","volume-title":"Graph attention networks. arXiv preprint arXiv:1710.10903","author":"Velickovi\u0107 Petar","year":"2017","unstructured":"Petar Velickovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)."},{"key":"e_1_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3003665.3003669"},{"key":"e_1_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCC.2016.7753651"},{"key":"e_1_2_2_57_1","volume-title":"Bayesian regularization and pruning using a Laplace prior. Neural computation","author":"Williams Peter M","year":"1995","unstructured":"Peter M Williams. 1995. Bayesian regularization and pruning using a Laplace prior. Neural computation, Vol. 7, 1 (1995), 117--143."},{"key":"e_1_2_2_58_1","first-page":"307","article-title":"Attention-based learning for missing data imputation in HoloClean","volume":"2","author":"Wu Richard","year":"2020","unstructured":"Richard Wu, Aoqian Zhang, Ihab Ilyas, and Theodoros Rekatsinas. 2020. Attention-based learning for missing data imputation in HoloClean. Proceedings of Machine Learning and Systems, Vol. 2 (2020), 307--325.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467066"},{"key":"e_1_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3069861"},{"key":"e_1_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3300085"},{"key":"e_1_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389720"},{"key":"e_1_2_2_63_1","volume-title":"Graph neural networks: A review of methods and applications. AI Open","author":"Zhou Jie","year":"2020","unstructured":"Jie Zhou, Ganqu Cui, Shengding Hu, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, and Maosong Sun. 2020. Graph neural networks: A review of methods and applications. AI Open (2020), 57--81."},{"key":"e_1_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/453"}],"container-title":["Proceedings of the ACM on Management of Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3588936","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3588936","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T12:47:37Z","timestamp":1750164457000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3588936"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,26]]},"references-count":64,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,5,26]]}},"alternative-id":["10.1145\/3588936"],"URL":"https:\/\/doi.org\/10.1145\/3588936","relation":{},"ISSN":["2836-6573"],"issn-type":[{"value":"2836-6573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,26]]}}}