{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T16:48:51Z","timestamp":1755794931808,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":70,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T00:00:00Z","timestamp":1752969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/100017437","name":"NASA Headquarters","doi-asserted-by":"publisher","id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/100017437","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Snapchat Gifts"},{"name":"Amazon Research Awards"},{"name":"SRC JUMP 2.0 Center"},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/100000002","name":"NIH (National Institutes of Health)","doi-asserted-by":"publisher","award":["U54HG012517, U24DK097771"],"award-info":[{"award-number":["U54HG012517, U24DK097771"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2211557, 1937599, 2119643, 2303037, 2312501, 2200274, 2106859"],"award-info":[{"award-number":["2211557, 1937599, 2119643, 2303037, 2312501, 2200274, 2106859"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Optum AI"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,20]]},"DOI":"10.1145\/3690624.3709262","type":"proceedings-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:44:43Z","timestamp":1743792283000},"page":"1691-1702","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Neural Network Pruning for Invariance Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2992-9768","authenticated-orcid":false,"given":"Derek","family":"Xu","sequence":"first","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0826-2697","authenticated-orcid":false,"given":"Yuanzhou","family":"Chen","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1812-6843","authenticated-orcid":false,"given":"Yizhou","family":"Sun","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8180-2886","authenticated-orcid":false,"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16826"},{"key":"e_1_3_2_1_2_1","volume-title":"International conference on machine learning. PMLR, 233--242","author":"Arpit Devansh","year":"2017","unstructured":"Devansh Arpit, Stanis\u0142aw Jastrz\u0119bski, Nicolas Ballas, David Krueger, Emmanuel Bengio, Maxinder S Kanwal, Tegan Maharaj, Asja Fischer, Aaron Courville, Yoshua Bengio, et al. 2017. A closer look at memorization in deep networks. In International conference on machine learning. PMLR, 233--242."},{"key":"e_1_3_2_1_3_1","unstructured":"Arthur Asuncion and David Newman. 2007. UCI machine learning repository."},{"key":"e_1_3_2_1_4_1","volume-title":"Scarf: Self-supervised contrastive learning using random feature corruption. arXiv preprint arXiv:2106.15147","author":"Bahri Dara","year":"2021","unstructured":"Dara Bahri, Heinrich Jiang, Yi Tay, and Donald Metzler. 2021. Scarf: Self-supervised contrastive learning using random feature corruption. arXiv preprint arXiv:2106.15147 (2021)."},{"key":"e_1_3_2_1_5_1","volume-title":"Learning invariances in neural networks from training data. Advances in neural information processing systems","author":"Benton Gregory","year":"2020","unstructured":"Gregory Benton, Marc Finzi, Pavel Izmailov, and Andrew G Wilson. 2020. Learning invariances in neural networks from training data. Advances in neural information processing systems, Vol. 33 (2020), 17605--17616."},{"key":"e_1_3_2_1_6_1","first-page":"129","article-title":"What is the state of neural network pruning","volume":"2","author":"Blalock Davis","year":"2020","unstructured":"Davis Blalock, Jose Javier Gonzalez Ortiz, Jonathan Frankle, and John Guttag. 2020. What is the state of neural network pruning? Proceedings of machine learning and systems, Vol. 2 (2020), 129--146.","journal-title":"Proceedings of machine learning and systems"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19894"},{"key":"e_1_3_2_1_9_1","volume-title":"Amortised invariance learning for contrastive self-supervision. arXiv preprint arXiv:2302.12712","author":"Chavhan Ruchika","year":"2023","unstructured":"Ruchika Chavhan, Henry Gouk, Jan Stuehmer, Calum Heggan, Mehrdad Yaghoobi, and Timothy Hospedales. 2023. Amortised invariance learning for contrastive self-supervision. arXiv preprint arXiv:2302.12712 (2023)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_1_11_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_3_2_1_12_1","volume-title":"On lazy training in differentiable programming. Advances in neural information processing systems","author":"Chizat Lenaic","year":"2019","unstructured":"Lenaic Chizat, Edouard Oyallon, and Francis Bach. 2019. On lazy training in differentiable programming. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_13_1","volume-title":"International conference on machine learning. PMLR, 2990--2999","author":"Cohen Taco","year":"2016","unstructured":"Taco Cohen and Max Welling. 2016. Group equivariant convolutional networks. In International conference on machine learning. PMLR, 2990--2999."},{"key":"e_1_3_2_1_14_1","volume-title":"Studying the impact of magnitude pruning on contrastive learning methods. arXiv preprint arXiv:2207.00200","author":"Corti Francesco","year":"2022","unstructured":"Francesco Corti, Rahim Entezari, Sara Hooker, Davide Bacciu, and Olga Saukh. 2022. Studying the impact of magnitude pruning on contrastive learning methods. arXiv preprint arXiv:2207.00200 (2022)."},{"key":"e_1_3_2_1_15_1","volume-title":"Equivariant contrastive learning. arXiv preprint arXiv:2111.00899","author":"Dangovski Rumen","year":"2021","unstructured":"Rumen Dangovski, Li Jing, Charlotte Loh, Seungwook Han, Akash Srivastava, Brian Cheung, Pulkit Agrawal, and Marin Solja\u010di\u0107. 2021. Equivariant contrastive learning. arXiv preprint arXiv:2111.00899 (2021)."},{"key":"e_1_3_2_1_16_1","volume-title":"Convolutional neural networks on graphs with fast localized spectral filtering. Advances in neural information processing systems","author":"Defferrard Micha\u00ebl","year":"2016","unstructured":"Micha\u00ebl Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. Advances in neural information processing systems, Vol. 29 (2016)."},{"key":"e_1_3_2_1_17_1","first-page":"28772","article-title":"Achieving rotational invariance with bessel-convolutional neural networks","volume":"34","author":"Delchevalerie Valentin","year":"2021","unstructured":"Valentin Delchevalerie, Adrien Bibal, Beno^it Fr\u00e9nay, and Alexandre Mayer. 2021. Achieving rotational invariance with bessel-convolutional neural networks. Advances in Neural Information Processing Systems, Vol. 34 (2021), 28772--28783.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01198"},{"key":"e_1_3_2_1_19_1","volume-title":"Why do self-supervised models transfer? investigating the impact of invariance on downstream tasks. arXiv preprint arXiv:2111.11398","author":"Ericsson Linus","year":"2021","unstructured":"Linus Ericsson, Henry Gouk, and Timothy M Hospedales. 2021. Why do self-supervised models transfer? investigating the impact of invariance on downstream tasks. arXiv preprint arXiv:2111.11398 (2021)."},{"key":"e_1_3_2_1_20_1","volume-title":"Valeriia Cherepanova, Chinmay Hegde, Frank Hutter, Micah Goldblum, Niv Cohen, and Colin White.","author":"Feuer Benjamin","year":"2024","unstructured":"Benjamin Feuer, Robin Tibor Schirrmeister, Valeriia Cherepanova, Chinmay Hegde, Frank Hutter, Micah Goldblum, Niv Cohen, and Colin White. 2024. TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks. arXiv preprint arXiv:2402.11137 (2024)."},{"key":"e_1_3_2_1_21_1","volume-title":"Improving transformation invariance in contrastive representation learning. arXiv preprint arXiv:2010.09515","author":"Foster Adam","year":"2020","unstructured":"Adam Foster, Rattana Pukdee, and Tom Rainforth. 2020. Improving transformation invariance in contrastive representation learning. arXiv preprint arXiv:2010.09515 (2020)."},{"key":"e_1_3_2_1_22_1","volume-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks. arXiv preprint arXiv:1803.03635","author":"Frankle Jonathan","year":"2018","unstructured":"Jonathan Frankle and Michael Carbin. 2018. The lottery ticket hypothesis: Finding sparse, trainable neural networks. arXiv preprint arXiv:1803.03635 (2018)."},{"key":"e_1_3_2_1_23_1","volume-title":"An open source AutoML benchmark. arXiv preprint arXiv:1907.00909","author":"Gijsbers Pieter","year":"2019","unstructured":"Pieter Gijsbers, Erin LeDell, Janek Thomas, S\u00e9bastien Poirier, Bernd Bischl, and Joaquin Vanschoren. 2019. An open source AutoML benchmark. arXiv preprint arXiv:1907.00909 (2019)."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 249--256","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 249--256."},{"volume-title":"Deep learning","author":"Goodfellow Ian","key":"e_1_3_2_1_25_1","unstructured":"Ian Goodfellow, Yoshua Bengio, Aaron Courville, and Yoshua Bengio. 2016. Deep learning. Vol. 1. MIT Press."},{"key":"e_1_3_2_1_26_1","volume-title":"Why do tree-based models still outperform deep learning on tabular data? arXiv preprint arXiv:2207.08815","author":"Grinsztajn L\u00e9o","year":"2022","unstructured":"L\u00e9o Grinsztajn, Edouard Oyallon, and Ga\u00ebl Varoquaux. 2022. Why do tree-based models still outperform deep learning on tabular data? arXiv preprint arXiv:2207.08815 (2022)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_29_1","volume-title":"Tabpfn: A transformer that solves small tabular classification problems in a second. arXiv preprint arXiv:2207.01848","author":"Hollmann Noah","year":"2022","unstructured":"Noah Hollmann, Samuel M\u00fcller, Katharina Eggensperger, and Frank Hutter. 2022. Tabpfn: A transformer that solves small tabular classification problems in a second. arXiv preprint arXiv:2207.01848 (2022)."},{"key":"e_1_3_2_1_30_1","volume-title":"What do compressed deep neural networks forget? arXiv preprint arXiv:1911.05248","author":"Hooker Sara","year":"2019","unstructured":"Sara Hooker, Aaron Courville, Gregory Clark, Yann Dauphin, and Andrea Frome. 2019. What do compressed deep neural networks forget? arXiv preprint arXiv:1911.05248 (2019)."},{"key":"e_1_3_2_1_31_1","volume-title":"Snapshot ensembles: Train 1, get m for free. arXiv preprint arXiv:1704.00109","author":"Huang Gao","year":"2017","unstructured":"Gao Huang, Yixuan Li, Geoff Pleiss, Zhuang Liu, John E Hopcroft, and Kilian Q Weinberger. 2017. Snapshot ensembles: Train 1, get m for free. arXiv preprint arXiv:1704.00109 (2017)."},{"key":"e_1_3_2_1_32_1","first-page":"12449","article-title":"Invariance learning in deep neural networks with differentiable Laplace approximations","volume":"35","author":"Immer Alexander","year":"2022","unstructured":"Alexander Immer, Tycho van der Ouderaa, Gunnar R\u00e4tsch, Vincent Fortuin, and Mark van der Wilk. 2022. Invariance learning in deep neural networks with differentiable Laplace approximations. Advances in Neural Information Processing Systems, Vol. 35 (2022), 12449--12463.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_33_1","unstructured":"Max Jaderberg Karen Simonyan Andrew Zisserman et al. 2015. Spatial transformer networks. Advances in neural information processing systems Vol. 28 (2015)."},{"key":"e_1_3_2_1_34_1","volume-title":"Well-tuned simple nets excel on tabular datasets. Advances in neural information processing systems","author":"Kadra Arlind","year":"2021","unstructured":"Arlind Kadra, Marius Lindauer, Frank Hutter, and Josif Grabocka. 2021. Well-tuned simple nets excel on tabular datasets. Advances in neural information processing systems, Vol. 34 (2021), 23928--23941."},{"key":"e_1_3_2_1_35_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_3_2_1_36_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_37_1","volume-title":"Deep learning. nature","author":"LeCun Yann","year":"2015","unstructured":"Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. nature, Vol. 521, 7553 (2015), 436--444."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_39_1","volume-title":"Snip: Single-shot network pruning based on connection sensitivity. arXiv preprint arXiv:1810.02340","author":"Lee Namhoon","year":"2018","unstructured":"Namhoon Lee, Thalaiyasingam Ajanthan, and Philip HS Torr. 2018. Snip: Single-shot network pruning based on connection sensitivity. arXiv preprint arXiv:1810.02340 (2018)."},{"key":"e_1_3_2_1_40_1","volume-title":"Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together! arXiv preprint arXiv:2303.02141","author":"Liu Shiwei","year":"2023","unstructured":"Shiwei Liu, Tianlong Chen, Zhenyu Zhang, Xuxi Chen, Tianjin Huang, Ajay Jaiswal, and Zhangyang Wang. 2023. Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together! arXiv preprint arXiv:2303.02141 (2023)."},{"key":"e_1_3_2_1_41_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_42_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_43_1","first-page":"12749","article-title":"Sanity checks for lottery tickets: Does your winning ticket really win the jackpot","volume":"34","author":"Ma Xiaolong","year":"2021","unstructured":"Xiaolong Ma, Geng Yuan, Xuan Shen, Tianlong Chen, Xuxi Chen, Xiaohan Chen, Ning Liu, Minghai Qin, Sijia Liu, Zhangyang Wang, et al. 2021. Sanity checks for lottery tickets: Does your winning ticket really win the jackpot? Advances in Neural Information Processing Systems, Vol. 34 (2021), 12749--12760.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_44_1","unstructured":"Duncan McElfresh Sujay Khandagale Jonathan Valverde Ganesh Ramakrishnan Micah Goldblum Colin White et al. 2023. When Do Neural Nets Outperform Boosted Trees on Tabular Data? arXiv preprint arXiv:2305.02997 (2023)."},{"key":"e_1_3_2_1_45_1","unstructured":"Yuval Netzer Tao Wang Adam Coates Alessandro Bissacco Bo Wu and Andrew Y Ng. 2011. Reading digits in natural images with unsupervised feature learning. (2011)."},{"key":"e_1_3_2_1_46_1","volume-title":"Implicit regularization in deep learning. arXiv preprint arXiv:1709.01953","author":"Neyshabur Behnam","year":"2017","unstructured":"Behnam Neyshabur. 2017. Implicit regularization in deep learning. arXiv preprint arXiv:1709.01953 (2017)."},{"key":"e_1_3_2_1_47_1","first-page":"8078","article-title":"Towards learning convolutions from scratch","volume":"33","author":"Neyshabur Behnam","year":"2020","unstructured":"Behnam Neyshabur. 2020. Towards learning convolutions from scratch. Advances in Neural Information Processing Systems, Vol. 33 (2020), 8078--8088.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_48_1","unstructured":"Behnam Neyshabur Ryota Tomioka and Nathan Srebro. 2014. In search of the real inductive bias: On the role of implicit regularization in deep learning. arXiv preprint arXiv:1412.6614 (2014)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"e_1_3_2_1_51_1","volume-title":"Pointnet: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems","author":"Qi Charles Ruizhongtai","year":"2017","unstructured":"Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J Guibas. 2017. Pointnet: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-15413-4_10"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CRV.2019.00010"},{"key":"e_1_3_2_1_54_1","volume-title":"TabReD: Analyzing Pitfalls and Filling the Gaps in Tabular Deep Learning Benchmarks. arXiv preprint arXiv:2406.19380","author":"Rubachev Ivan","year":"2024","unstructured":"Ivan Rubachev, Nikolay Kartashev, Yury Gorishniy, and Artem Babenko. 2024. TabReD: Analyzing Pitfalls and Filling the Gaps in Tabular Deep Learning Benchmarks. arXiv preprint arXiv:2406.19380 (2024)."},{"key":"e_1_3_2_1_55_1","volume-title":"Dynamic routing between capsules. Advances in neural information processing systems","author":"Sabour Sara","year":"2017","unstructured":"Sara Sabour, Nicholas Frosst, and Geoffrey E Hinton. 2017. Dynamic routing between capsules. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_56_1","volume-title":"International conference on machine learning. PMLR, 9323--9332","author":"Satorras Victor Garcia","year":"2021","unstructured":"Victor Garcia Satorras, Emiel Hoogeboom, and Max Welling. 2021. E (n) equivariant graph neural networks. In International conference on machine learning. PMLR, 9323--9332."},{"key":"e_1_3_2_1_57_1","first-page":"1858","article-title":"Shift invariance can reduce adversarial robustness","volume":"34","author":"Singla Vasu","year":"2021","unstructured":"Vasu Singla, Songwei Ge, Basri Ronen, and David Jacobs. 2021. Shift invariance can reduce adversarial robustness. Advances in Neural Information Processing Systems, Vol. 34 (2021), 1858--1871.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"e_1_3_2_1_59_1","volume-title":"A simple and effective pruning approach for large language models. arXiv preprint arXiv:2306.11695","author":"Sun Mingjie","year":"2023","unstructured":"Mingjie Sun, Zhuang Liu, Anna Bair, and J Zico Kolter. 2023. A simple and effective pruning approach for large language models. arXiv preprint arXiv:2306.11695 (2023)."},{"key":"e_1_3_2_1_60_1","volume-title":"Commonsenseqa: A question answering challenge targeting commonsense knowledge. arXiv preprint arXiv:1811.00937","author":"Talmor Alon","year":"2018","unstructured":"Alon Talmor, Jonathan Herzig, Nicholas Lourie, and Jonathan Berant. 2018. Commonsenseqa: A question answering challenge targeting commonsense knowledge. arXiv preprint arXiv:1811.00937 (2018)."},{"key":"e_1_3_2_1_61_1","volume-title":"arXiv preprint arXiv:2406.05207","author":"Thomas Valentin","year":"2024","unstructured":"Valentin Thomas, Junwei Ma, Rasa Hosseinzadeh, Keyvan Golestan, Guangwei Yu, Maksims Volkovs, and Anthony Caterini. 2024. Retrieval & Fine-Tuning for In-Context Tabular Models. arXiv preprint arXiv:2406.05207 (2024)."},{"key":"e_1_3_2_1_62_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 9446--9454","author":"Ulyanov Dmitry","year":"2018","unstructured":"Dmitry Ulyanov, Andrea Vedaldi, and Victor Lempitsky. 2018. Deep image prior. In Proceedings of the IEEE conference on computer vision and pattern recognition. 9446--9454."},{"key":"e_1_3_2_1_63_1","volume-title":"Picking winning tickets before training by preserving gradient flow. arXiv preprint arXiv:2002.07376","author":"Wang Chaoqi","year":"2020","unstructured":"Chaoqi Wang, Guodong Zhang, and Roger Grosse. 2020. Picking winning tickets before training by preserving gradient flow. arXiv preprint arXiv:2002.07376 (2020)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_2_1_65_1","volume-title":"Mixture of In-Context Prompters for Tabular PFNs. arXiv preprint arXiv:2405.16156","author":"Xu Derek","year":"2024","unstructured":"Derek Xu, Olcay Cirit, Reza Asadi, Yizhou Sun, and Wei Wang. 2024. Mixture of In-Context Prompters for Tabular PFNs. arXiv preprint arXiv:2405.16156 (2024)."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21408"},{"key":"e_1_3_2_1_67_1","volume-title":"Scale-invariant convolutional neural networks. arXiv preprint arXiv:1411.6369","author":"Xu Yichong","year":"2014","unstructured":"Yichong Xu, Tianjun Xiao, Jiaxing Zhang, Kuiyuan Yang, and Zheng Zhang. 2014. Scale-invariant convolutional neural networks. arXiv preprint arXiv:1411.6369 (2014)."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"e_1_3_2_1_69_1","volume-title":"Revisiting few-sample BERT fine-tuning. arXiv preprint arXiv:2006.05987","author":"Zhang Tianyi","year":"2020","unstructured":"Tianyi Zhang, Felix Wu, Arzoo Katiyar, Kilian Q Weinberger, and Yoav Artzi. 2020. Revisiting few-sample BERT fine-tuning. arXiv preprint arXiv:2006.05987 (2020)."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3067763"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Toronto ON Canada","acronym":"KDD '25"},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709262","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3690624.3709262","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T15:43:56Z","timestamp":1755359036000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709262"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"references-count":70,"alternative-id":["10.1145\/3690624.3709262","10.1145\/3690624"],"URL":"https:\/\/doi.org\/10.1145\/3690624.3709262","relation":{},"subject":[],"published":{"date-parts":[[2025,7,20]]},"assertion":[{"value":"2025-07-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}