{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T07:02:21Z","timestamp":1780729341847,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":38,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819214617","type":"print"},{"value":"9789819214624","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-92-1462-4_35","type":"book-chapter","created":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T06:46:19Z","timestamp":1780728379000},"page":"444-457","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DrIM: Context-Driven Nearest Neighbor Imputation Using Language Representation"],"prefix":"10.1007","author":[{"given":"Jaesung","family":"Lim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seunghwan","family":"An","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jong-June","family":"Jeon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,7]]},"reference":[{"key":"35_CR1","unstructured":"Bachman, P., Hjelm, R.D., Buchwalter, W.: Learning representations by maximizing mutual information across views. In: NeurIPS (2019)"},{"key":"35_CR2","unstructured":"Black, S., Gao, L., Wang, P., Leahy, C., Biderman, S.: Gpt-neo: large scale autoregressive language modeling with mesh-tensorflow (2021)"},{"key":"35_CR3","unstructured":"Borisov, V., Sessler, K., Leemann, T., Pawelczyk, M., Kasneci, G.: Language models are realistic tabular data generators. In: ICLR (2023)"},{"issue":"3","key":"35_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v045.i03","volume":"45","author":"S van Buuren","year":"2011","unstructured":"van Buuren, S., Groothuis-Oudshoorn, K.: mice: Multivariate imputation by chained equations in r. J. Stat. Softw. 45(3), 1\u201367 (2011)","journal-title":"J. Stat. Softw."},{"key":"35_CR5","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML (2020)"},{"key":"35_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (2019)"},{"key":"35_CR7","unstructured":"Du, T., Melis, L., Wang, T.: Remasker: imputing tabular data with masked autoencoding. In: ICLR (2024)"},{"key":"35_CR8","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1016\/j.ins.2022.01.056","volume":"592","author":"S Faisal","year":"2022","unstructured":"Faisal, S., Tutz, G.: Nearest neighbor imputation for categorical data by weighting of attributes. Inf. Sci. 592, 306\u2013319 (2022)","journal-title":"Inf. Sci."},{"key":"35_CR9","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1007\/s00521-009-0295-6","volume":"19","author":"PJ Garc\u00eda-Laencina","year":"2010","unstructured":"Garc\u00eda-Laencina, P.J., Sancho-G\u00f3mez, J.L., Figueiras-Vidal, A.R.: Pattern classification with missing data: a review. Neural Comput. Appl. 19, 263\u2013282 (2010)","journal-title":"Neural Comput. Appl."},{"key":"35_CR10","unstructured":"Hayat, A., Hasan, M.R.: A context-aware approach for enhancing data imputation with pre-trained language models. In: COLING (2025)"},{"key":"35_CR11","unstructured":"Ipsen, N.B., Mattei, P.A., Frellsen, J.: not-miwae: deep generative modelling with missing not at random data. In: ICLR (2021)"},{"key":"35_CR12","unstructured":"Ivanov, O., Figurnov, M., Vetrov, D.: Variational autoencoder with arbitrary conditioning. In: ICLR (2019)"},{"issue":"10","key":"35_CR13","doi-asserted-by":"publisher","first-page":"913","DOI":"10.1080\/08839514.2019.1637138","volume":"33","author":"A Jadhav","year":"2019","unstructured":"Jadhav, A., Pramod, D., Ramanathan, K.: Comparison of performance of data imputation methods for numeric dataset. Appl. Artif. Intell. 33(10), 913\u2013933 (2019)","journal-title":"Appl. Artif. Intell."},{"key":"35_CR14","unstructured":"Kyono, T., Zhang, Y., Bellot, A., van\u00a0der Schaar, M.: MIRACLE: causally-aware imputation via learning missing data mechanisms. In: NeurIPS (2021)"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Little, R., Rubin, D.: Statistical analysis with missing data. Wiley series in probability and mathematical statistics, Wiley (2002)","DOI":"10.1002\/9781119013563"},{"key":"35_CR16","unstructured":"Liu, Y., et al.: .: Roberta: A robustly optimized bert pretraining approach ArXiv abs\/ arXiv:1907.11692 (2019)"},{"key":"35_CR17","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2017)"},{"key":"35_CR18","unstructured":"Mattei, P.A., Frellsen, J.: MIWAE: deep generative modelling and imputation of incomplete data sets. In: ICML (2019)"},{"key":"35_CR19","first-page":"2287","volume":"11","author":"R Mazumder","year":"2010","unstructured":"Mazumder, R., Hastie, T., Tibshirani, R.: Spectral regularization algorithms for learning large incomplete matrices. J. Mach. Learn. Res. 11, 2287\u20132322 (2010)","journal-title":"J. Mach. Learn. Res."},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Mei, Y., Song, S., Fang, C., Yang, H., Fang, J., Long, J.: Capturing semantics for imputation with pre-trained language models. In: ICDE (2021)","DOI":"10.1109\/ICDE51399.2021.00013"},{"key":"35_CR21","unstructured":"Mikolov, T., Chen, K., Corrado, G.S., Dean, J.: Efficient estimation of word representations in vector space. In: ICLR (2013)"},{"key":"35_CR22","unstructured":"Morvan, M.L., Varoquaux, G.: Imputation for prediction: beware of diminishing returns. In: ICLR (2025)"},{"key":"35_CR23","unstructured":"Mu\u00f1oz, L.A.B., Hern\u00e1ndez-Gonz\u00e1lez, J.: Similarity networks for heterogeneous data. In: The European Symposium on Artificial Neural Networks (2012)"},{"key":"35_CR24","unstructured":"Muzellec, B., Josse, J., Boyer, C., Cuturi, M.: Missing data imputation using optimal transport. In: ICML (2020)"},{"issue":"11","key":"35_CR25","first-page":"1514","volume":"93","author":"FV Nelwamondo","year":"2007","unstructured":"Nelwamondo, F.V., Mohamed, S., Marwala, T.: Missing data: a comparison of neural network and expectation maximization techniques. Curr. Sci. 93(11), 1514\u20131521 (2007)","journal-title":"Curr. Sci."},{"key":"35_CR26","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019)"},{"key":"35_CR27","unstructured":"Rubin, D.B.: Multiple imputation for nonresponse in surveys (1989)"},{"key":"35_CR28","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.patrec.2020.05.032","volume":"136","author":"MS Santos","year":"2020","unstructured":"Santos, M.S., Abreu, P.H., Wilk, S., Santos, J.A.M.: How distance metrics influence missing data imputation with k-nearest neighbours. Pattern Recognit. Lett. 136, 111\u2013119 (2020)","journal-title":"Pattern Recognit. Lett."},{"issue":"231","key":"35_CR29","first-page":"1","volume":"23","author":"H Sasaki","year":"2022","unstructured":"Sasaki, H., Takenouchi, T.: Representation learning for maximization of mi, nonlinear ica and nonlinear subspaces with robust density ratio estimation. J. Mach. Learn. Res. 23(231), 1\u201355 (2022)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"35_CR30","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1093\/bioinformatics\/btr597","volume":"28","author":"DJ Stekhoven","year":"2012","unstructured":"Stekhoven, D.J., B\u00fchlmann, P.: Missforest\u2013non-parametric missing value imputation for mixed-type data. Bioinformatics 28(1), 112\u2013118 (2012)","journal-title":"Bioinformatics"},{"key":"35_CR31","doi-asserted-by":"crossref","unstructured":"Sugiyama, M., Suzuki, T., Kanamori, T.: Density Ratio Estimation in Machine Learning, 1st edn. Cambridge University Press, USA (2012)","DOI":"10.1017\/CBO9781139035613"},{"key":"35_CR32","unstructured":"Touvron, H., et al.: Llama: Open and efficient foundation language models, ArXiv abs\/ arXiv:2302.13971 (2023)"},{"issue":"6","key":"35_CR33","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1093\/bioinformatics\/17.6.520","volume":"17","author":"OG Troyanskaya","year":"2001","unstructured":"Troyanskaya, O.G., et al.: Missing value estimation methods for dna microarrays. Bioinformatics 17(6), 520\u20135 (2001)","journal-title":"Bioinformatics"},{"key":"35_CR34","doi-asserted-by":"crossref","unstructured":"Van Buuren, S.: Flexible imputation of missing data. CRC Press (2018)","DOI":"10.1201\/9780429492259"},{"issue":"1","key":"35_CR35","first-page":"1","volume":"6","author":"DR Wilson","year":"1997","unstructured":"Wilson, D.R., Martinez, T.R.: Improved heterogeneous distance functions. J. Artif. Int. Res. 6(1), 1\u201334 (1997)","journal-title":"J. Artif. Int. Res."},{"key":"35_CR36","unstructured":"Wu, X., Gao, C., Zang, L., Han, J., Wang, Z., Hu, S.: ESimCSE: enhanced sample building method for contrastive learning of unsupervised sentence embedding. In: COLING (2022)"},{"key":"35_CR37","unstructured":"Yoon, J., Jordon, J., van\u00a0der Schaar, M.: GAIN: Missing data imputation using generative adversarial nets. In: ICML (2018)"},{"key":"35_CR38","unstructured":"Zhao, H., Sun, K., Dezfouli, A., Bonilla, E.V.: Transformed distribution matching for missing value imputation. In: ICML (2023)"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-1462-4_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T06:46:23Z","timestamp":1780728383000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-1462-4_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819214617","9789819214624"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-1462-4_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"7 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pakdd2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}