{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T21:18:01Z","timestamp":1787692681621,"version":"build-2784847793"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","funder":[{"name":"Nanyang Technological University","award":["RSR and SUG"],"award-info":[{"award-number":["RSR and SUG"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3780320","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:07:40Z","timestamp":1785499660000},"page":"612-620","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Offline Behavioral Data Selection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7810-9346","authenticated-orcid":false,"given":"Shiye","family":"Lei","sequence":"first","affiliation":[{"name":"School of Computer Science, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8360-5149","authenticated-orcid":false,"given":"Zhihao","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"College of Computing & Data Science, Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Michael Bain and Claude Sammut. 1995. A Framework for Behavioural Cloning.. In Machine intelligence 15. 103-129.","DOI":"10.1093\/oso\/9780198538677.003.0006"},{"key":"e_1_3_2_1_2_1","volume-title":"Davide Del Testa","author":"Bojarski Mariusz","year":"2016","unstructured":"Mariusz Bojarski, Davide Del Testa, Daniel Dworakowski, Bernhard Firner, Beat Flepp, Prasoon Goyal, Lawrence D Jackel, Mathew Monfort, Urs Muller, Jiakai Zhang, et al., 2016. End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316 (2016)."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the Third International Conference on Automated Machine Learning (Proceedings of Machine Learning Research","volume":"23","author":"Vishak Prasad","year":"2024","unstructured":"Vishak Prasad C, Colin White, Sibasis Nayak, Paarth Jain, Aziz Shameem, Prateek Garg, and Ganesh Ramakrishnan. 2024. Speeding up NAS with Adaptive Subset Selection. In Proceedings of the Third International Conference on Automated Machine Learning (Proceedings of Machine Learning Research, Vol. 256), Katharina Eggensperger, Roman Garnett, Joaquin Vanschoren, Marius Lindauer, and Jacob R. Gardner (Eds.). PMLR, 3\/1-23. https:\/\/proceedings.mlr.press\/v256\/c24a.html"},{"key":"e_1_3_2_1_4_1","volume-title":"International symposium on experimental robotics. Springer, 3-11","author":"Daftry Shreyansh","year":"2016","unstructured":"Shreyansh Daftry, J Andrew Bagnell, and Martial Hebert. 2016. Learning transferable policies for monocular reactive mav control. In International symposium on experimental robotics. Springer, 3-11."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_6_1","unstructured":"Justin Fu Aviral Kumar Ofir Nachum George Tucker and Sergey Levine. 2020. D4RL: Datasets for Deep Data-Driven Reinforcement Learning. arXiv:2004.07219 [cs.LG]"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2015.2509024"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-12423-5_14"},{"key":"e_1_3_2_1_9_1","volume-title":"International conference on machine learning. PMLR","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine. 2018. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International conference on machine learning. PMLR, 1861-1870."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2220"},{"key":"e_1_3_2_1_11_1","volume-title":"International Conference on Machine Learning. PMLR, 5464-5474","author":"Killamsetty Krishnateja","year":"2021","unstructured":"Krishnateja Killamsetty, Sivasubramanian Durga, Ganesh Ramakrishnan, Abir De, and Rishabh Iyer. 2021. Grad-match: Gradient matching based data subset selection for efficient deep model training. In International Conference on Machine Learning. PMLR, 5464-5474."},{"key":"e_1_3_2_1_12_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_2_1_13_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_14_1","volume-title":"State Diversity Matters in Offline Behavior Distillation. arXiv preprint arXiv:2512.06692","author":"Lei Shiye","year":"2025","unstructured":"Shiye Lei, Zhihao Cheng, and Dacheng Tao. 2025. State Diversity Matters in Offline Behavior Distillation. arXiv preprint arXiv:2512.06692 (2025)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3322540"},{"key":"e_1_3_2_1_16_1","volume-title":"Offline Behavior Distillation. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=89fSR2gpxp","author":"Lei Shiye","year":"2024","unstructured":"Shiye Lei, Sen Zhang, and Dacheng Tao. 2024. Offline Behavior Distillation. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=89fSR2gpxp"},{"key":"e_1_3_2_1_17_1","volume-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643","author":"Levine Sergey","year":"2020","unstructured":"Sergey Levine, Aviral Kumar, George Tucker, and Justin Fu. 2020. Offline reinforcement learning: Tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643 (2020)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.3002505"},{"key":"e_1_3_2_1_19_1","volume-title":"International Conference on Machine Learning. PMLR, 6950-6960","author":"Mirzasoleiman Baharan","year":"2020","unstructured":"Baharan Mirzasoleiman, Jeff Bilmes, and Jure Leskovec. 2020. Coresets for data-efficient training of machine learning models. In International Conference on Machine Learning. PMLR, 6950-6960."},{"key":"e_1_3_2_1_20_1","volume-title":"Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=GcEIvidYSw","author":"Nakamoto Mitsuhiko","year":"2023","unstructured":"Mitsuhiko Nakamoto, Yuexiang Zhai, Anikait Singh, Max Sobol Mark, Yi Ma, Chelsea Finn, Aviral Kumar, and Sergey Levine. 2023. Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=GcEIvidYSw"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914554471"},{"key":"e_1_3_2_1_22_1","volume-title":"NeurIPS 2024 Workshop on Fine-Tuning in Modern Machine Learning: Principles and Scalability.","author":"Noh Samyeul","unstructured":"Samyeul Noh, Seonghyun Kim, and Ingook Jang. [n.d.]. Efficient Fine-Tuning of Behavior Cloned Policies with Reinforcement Learning from Limited Demonstrations. In NeurIPS 2024 Workshop on Fine-Tuning in Modern Machine Learning: Principles and Scalability."},{"key":"e_1_3_2_1_23_1","volume-title":"NeurIPS 2022 Workshop.","author":"Park Dongmin","year":"2022","unstructured":"Dongmin Park, Dimitris Papailiopoulos, and Kangwook Lee. 2022. Active learning is a strong baseline for data subset selection. In Has it Trained Yet? NeurIPS 2022 Workshop."},{"key":"e_1_3_2_1_24_1","volume-title":"Deep learning on a data diet: Finding important examples early in training. Advances in neural information processing systems","author":"Paul Mansheej","year":"2021","unstructured":"Mansheej Paul, Surya Ganguli, and Gintare Karolina Dziugaite. 2021. Deep learning on a data diet: Finding important examples early in training. Advances in neural information processing systems, Vol. 34 (2021), 20596-20607."},{"key":"e_1_3_2_1_25_1","volume-title":"Efficient training of artificial neural networks for autonomous navigation. Neural computation","author":"Pomerleau Dean A","year":"1991","unstructured":"Dean A Pomerleau. 1991. Efficient training of artificial neural networks for autonomous navigation. Neural computation, Vol. 3, 1 (1991), 88-97."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 661-668","author":"Ross St\u00e9phane","year":"2010","unstructured":"St\u00e9phane Ross and Drew Bagnell. 2010. Efficient reductions for imitation learning. In Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 661-668."},{"key":"e_1_3_2_1_27_1","volume-title":"Active Learning for Convolutional Neural Networks: A Core-Set Approach. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=H1aIuk-RW","author":"Sener Ozan","year":"2018","unstructured":"Ozan Sener and Silvio Savarese. 2018. Active Learning for Convolutional Neural Networks: A Core-Set Approach. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=H1aIuk-RW"},{"key":"e_1_3_2_1_28_1","volume-title":"Core-set sampling for efficient neural architecture search. arXiv preprint arXiv:2107.06869","author":"Kong Kyeongbo","year":"2021","unstructured":"Jae-hun Shim, Kyeongbo Kong, and Suk-Ju Kang. 2021. Core-set sampling for efficient neural architecture search. arXiv preprint arXiv:2107.06869 (2021)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/3312046"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00020"},{"key":"e_1_3_2_1_31_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=BJlxm30cKm","author":"Toneva Mariya","unstructured":"Mariya Toneva, Alessandro Sordoni, Remi Tachet des Combes, Adam Trischler, Yoshua Bengio, and Geoffrey J. Gordon. 2019. An Empirical Study of Example Forgetting during Deep Neural Network Learning. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=BJlxm30cKm"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"e_1_3_2_1_33_1","volume-title":"Dataset distillation. arXiv preprint arXiv:1811.10959","author":"Wang Tongzhou","year":"2018","unstructured":"Tongzhou Wang, Jun-Yan Zhu, Antonio Torralba, and Alexei A Efros. 2018. Dataset distillation. arXiv preprint arXiv:1811.10959 (2018)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553517"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","first-page":"6304","DOI":"10.52202\/068431-0456","article-title":"Disentangling transfer in continual reinforcement learning","volume":"35","author":"Wolczyk Maciej","year":"2022","unstructured":"Maciej Wolczyk, Micha\u0142 Zaj\u0105c, Razvan Pascanu, \u0141ukasz Kuci'nski, and Piotr Mi\u0142o's. 2022. Disentangling transfer in continual reinforcement learning. Advances in Neural Information Processing Systems, Vol. 35 (2022), 6304-6317.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","first-page":"22354","DOI":"10.52202\/068431-1624","article-title":"Active learning through a covering lens","volume":"35","author":"Yehuda Ofer","year":"2022","unstructured":"Ofer Yehuda, Avihu Dekel, Guy Hacohen, and Daphna Weinshall. 2022. Active learning through a covering lens. Advances in Neural Information Processing Systems, Vol. 35 (2022), 22354-22367.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","volume-title":"Online Coreset Selection for Rehearsal-based Continual Learning. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=f9D-5WNG4Nv","author":"Yoon Jaehong","year":"2022","unstructured":"Jaehong Yoon, Divyam Madaan, Eunho Yang, and Sung Ju Hwang. 2022. Online Coreset Selection for Rehearsal-based Continual Learning. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=f9D-5WNG4Nv"},{"key":"e_1_3_2_1_38_1","volume-title":"Dataset Condensation with Gradient Matching. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=mSAKhLYLSsl","author":"Zhao Bo","year":"2021","unstructured":"Bo Zhao, Konda Reddy Mopuri, and Hakan Bilen. 2021. Dataset Condensation with Gradient Matching. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=mSAKhLYLSsl"},{"key":"e_1_3_2_1_39_1","volume-title":"International conference on machine learning. PMLR, 27287-27302","author":"Zhou Xiao","year":"2022","unstructured":"Xiao Zhou, Renjie Pi, Weizhong Zhang, Yong Lin, Zonghao Chen, and Tong Zhang. 2022. Probabilistic bilevel coreset selection. In International conference on machine learning. PMLR, 27287-27302."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3780320","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:18:28Z","timestamp":1787689108000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3780320"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":39,"alternative-id":["10.1145\/3770854.3780320","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3780320","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}