{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T02:11:54Z","timestamp":1765505514064,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3760971","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:36:36Z","timestamp":1762562196000},"page":"5181-5185","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Equitable Coreset Selection: Addressing Challenges Under Class Imbalance"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9106-3715","authenticated-orcid":false,"given":"Liyana","family":"Sahir Kallooriyakath","sequence":"first","affiliation":[{"name":"AI Garage, Mastercard, Gurugram, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3135-7291","authenticated-orcid":false,"given":"Anugu Namratha","family":"Reddy","sequence":"additional","affiliation":[{"name":"AI Garage, Mastercard, Gurugram, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5656-2899","authenticated-orcid":false,"given":"B Srinath","family":"Achary","sequence":"additional","affiliation":[{"name":"AI Garage, Mastercard, Gurugram, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2594-7861","authenticated-orcid":false,"given":"Ashutosh","family":"Sharma","sequence":"additional","affiliation":[{"name":"AI Garage, Mastercard, Gurugram, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4219-0527","authenticated-orcid":false,"given":"Krisha","family":"Shah","sequence":"additional","affiliation":[{"name":"AI Garage, Mastercard, Gurugram, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6143-8653","authenticated-orcid":false,"given":"Sonia","family":"Gupta","sequence":"additional","affiliation":[{"name":"AI Garage, Mastercard, Gurugram, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6798-1240","authenticated-orcid":false,"given":"Siddhartha","family":"Asthana","sequence":"additional","affiliation":[{"name":"AI Garage, Mastercard, Gurugram, India"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Westland","author":"Bhattacharyya S.","year":"2011","unstructured":"Bhattacharyya, S., Jha, S., Tharakunnel, K., Westland, J.C.: Data mining for credit card fraud: A comparative study. Decision support systems 50(3), 602--613 (2011)"},{"key":"e_1_3_2_1_2_1","volume-title":"Ma","author":"Cao K.","year":"2019","unstructured":"Cao, K., Wei, C., Gaidon, A., Arechiga, N., Ma, T.: Learning imbalanced datasets with label-distribution-aware margin loss. In: Advances in Neural Information Processing Systems (NeurIPS). vol. 32 (2019)"},{"key":"e_1_3_2_1_3_1","volume-title":"Kumar","author":"Chandola V.","year":"2009","unstructured":"Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection: A survey. ACM computing surveys (CSUR) 41(3), 1--58 (2009)"},{"volume-title":"Proceedings of the International Conference on Learning Representations (ICLR) (2019)","author":"Coleman C.","key":"e_1_3_2_1_4_1","unstructured":"Coleman, C., Yeh, C., Mussmann, S., Mirzasoleiman, B., Bailis, P., Liang, P., Leskovec, J., Zaharia, M.: Selection via proxy: Efficient data selection for deep learning. In: Proceedings of the International Conference on Learning Representations (ICLR) (2019)"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-12423-5_14"},{"key":"e_1_3_2_1_6_1","first-page":"39382","volume":"36","author":"He Y.","year":"2023","unstructured":"He, Y., Xiao, L., Zhou, J.T.: You only condense once: Two rules for pruning condensed datasets. Advances in Neural Information Processing Systems 36, 39382--39394 (2023)","journal-title":"Neural Information Processing Systems"},{"key":"e_1_3_2_1_7_1","first-page":"722","volume-title":"Asanani","author":"Iyer R.","year":"2021","unstructured":"Iyer, R., Khargoankar, N., Bilmes, J., Asanani, H.: Submodular combinatorial information measures with applications in machine learning. In: Algorithmic Learning Theory. pp. 722--754. PMLR (2021)"},{"volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (2021)","author":"Killamsetty K.","key":"e_1_3_2_1_8_1","unstructured":"Killamsetty, K., Sivasubramanian, D., Ramakrishnan, G., Iyer, R.: Glister: Generalization based data subset selection for efficient and robust learning. In: Proceedings of the AAAI Conference on Artificial Intelligence (2021)"},{"key":"e_1_3_2_1_9_1","volume-title":"Hinton","author":"Krizhevsky A.","year":"2009","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Tech. rep., Citeseer (2009)"},{"key":"e_1_3_2_1_10_1","volume-title":"Yang","author":"Le Y.","year":"2015","unstructured":"Le, Y., Yang, X.: Tiny imagenet visual recognition challenge. CS 231N Course Project Report (2015), https:\/\/tinyimagenet.herokuapp.com\/, stanford University"},{"key":"e_1_3_2_1_11_1","first-page":"6950","volume-title":"International Conference on Machine Learning.","author":"Mirzasoleiman B.","year":"2020","unstructured":"Mirzasoleiman, B., Bilmes, J., Leskovec, J.: Coresets for data-efficient training of machine learning models. In: International Conference on Machine Learning. pp. 6950--6960. PMLR (2020)"},{"key":"e_1_3_2_1_12_1","volume-title":"Dziugaite","author":"Paul M.","year":"2059","unstructured":"Paul, M., Ganguli, S., Dziugaite, G.K.: Deep learning on a data diet: Finding important examples early in training. Advances in neural information processing systems 34, 20596--20607 (2021)"},{"key":"e_1_3_2_1_13_1","first-page":"17044","volume":"33","author":"Pleiss G.","year":"2020","unstructured":"Pleiss, G., Zhang, T., Elenberg, E., Weinberger, K.Q.: Identifying mislabeled data using the area under the margin ranking. Advances in Neural Information Processing Systems 33, 17044--17056 (2020)","journal-title":"Neural Information Processing Systems"},{"volume-title":"Proceedings of the International Conference on Learning Representations (ICLR) (2018)","author":"Sener O.","key":"e_1_3_2_1_14_1","unstructured":"Sener, O., Savarese, S.: Active learning for convolutional neural networks: A coreset approach. In: Proceedings of the International Conference on Learning Representations (ICLR) (2018)"},{"key":"e_1_3_2_1_15_1","first-page":"19523","volume":"35","author":"Sorscher B.","year":"2022","unstructured":"Sorscher, B., Geirhos, R., Shekhar, S., Ganguli, S., Morcos, A.: Beyond neural scaling laws: beating power law scaling via data pruning. Advances in Neural Information Processing Systems 35, 19523--19536 (2022)","journal-title":"Neural Information Processing Systems"},{"volume-title":"International Conference on Learning Representations (ICLR) (2019)","author":"Toneva M.","key":"e_1_3_2_1_16_1","unstructured":"Toneva, M., Sordoni, A., des Combes, R.T., Trischler, A., Bengio, Y., Gordon, G.J.: An empirical study of example forgetting during deep neural network learning. In: International Conference on Learning Representations (ICLR) (2019)"},{"volume-title":"Liu","author":"Xia X.","key":"e_1_3_2_1_17_1","unstructured":"Xia, X., Liu, J., Yu, J., Shen, X., Han, B., Liu, T.: Moderate coreset: A universal method of data selection for real-world data-efficient deep learning (2022)"},{"volume-title":"Forty-first International Conference on Machine Learning (2024)","author":"Yang S.","key":"e_1_3_2_1_18_1","unstructured":"Yang, S., Cao, Z., Guo, S., Zhang, R., Luo, P., Zhang, S., Nie, L.: Mind the boundary: Coreset selection via reconstructing the decision boundary. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"e_1_3_2_1_19_1","first-page":"116113","volume":"189","author":"Zhao H.","year":"2022","unstructured":"Zhao, H., Wang, R., Lei, Y., Liao, W.H., Cao, H., Cao, J.: Severity level diagnosis of parkinson's disease by ensemble k-nearest neighbor under imbalanced data. Expert Systems with Applications 189, 116113 (2022)","journal-title":"Applications"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472813.3472817"},{"key":"e_1_3_2_1_21_1","volume-title":"Prakash","author":"Zheng H.","year":"2022","unstructured":"Zheng, H., Liu, R., Lai, F., Prakash, A.: Coverage-centric coreset selection for high pruning rates. ArXiv abs\/2210.15809 (2022)"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Seoul Republic of Korea","acronym":"CIKM '25"},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3760971","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T02:08:13Z","timestamp":1765505293000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3760971"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":21,"alternative-id":["10.1145\/3746252.3760971","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3760971","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}