{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T12:21:13Z","timestamp":1780316473682,"version":"3.54.1"},"reference-count":62,"publisher":"Association for Computing Machinery (ACM)","issue":"1","funder":[{"name":"National NSF of China","award":["62302176, 62072046, 62302181"],"award-info":[{"award-number":["62302176, 62072046, 62302181"]}]},{"name":"Key R&D Program of Hubei Province","award":["2023BAB017, 2023BAB079"],"award-info":[{"award-number":["2023BAB017, 2023BAB079"]}]},{"name":"Knowledge Innovation Program of Wuhan-Basic Research","award":["2022010801010083"],"award-info":[{"award-number":["2022010801010083"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2026,1,31]]},"abstract":"<jats:p>Deep Neural Networks (DNNs), extensively applied across diverse disciplines, are characterized by their integrated and monolithic architectures, setting them apart from conventional software systems. This architectural difference introduces particular challenges to maintenance tasks, such as model restructure (e.g., model compression), re-adaptation (e.g., fitting new samples), and incremental development (e.g., continual knowledge accumulation).<\/jats:p>\n                  <jats:p>Prior research addresses these challenges by identifying task-critical neuron layers and dividing neural networks into semantically similar sequential modules. However, such layer-level approaches fail to precisely identify and manipulate neuron-level semantic components, restricting their applicability to finer-grained model maintenance tasks.<\/jats:p>\n                  <jats:p>\n                    In this work, we implement NeuSemSlice, a novel framework that introduces the\n                    <jats:italic toggle=\"yes\">semantic slicing<\/jats:italic>\n                    technique to effectively identify critical neuron-level semantic components in DNN models for\n                    <jats:italic toggle=\"yes\">semantic-aware model maintenance<\/jats:italic>\n                    tasks. Specifically,\n                    <jats:italic toggle=\"yes\">semantic slicing<\/jats:italic>\n                    identifies, categorizes, and merges critical neurons across different categories and layers according to their semantic similarity, enabling their flexibility and effectiveness in the subsequent tasks.\n                  <\/jats:p>\n                  <jats:p>\n                    For\n                    <jats:italic toggle=\"yes\">semantic-aware model maintenance<\/jats:italic>\n                    tasks, we provide a series of novel strategies based on\n                    <jats:italic toggle=\"yes\">semantic slicing<\/jats:italic>\n                    to enhance NeuSemSlice. They include semantic components (i.e., critical neurons) preservation for model restructure, critical neuron tuning for model re-adaptation, and non-critical neuron training for model incremental development. A thorough evaluation has demonstrated that NeuSemSlice significantly outperforms baselines in all three tasks.\n                  <\/jats:p>","DOI":"10.1145\/3731556","type":"journal-article","created":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T10:35:11Z","timestamp":1745404511000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["NeuSemSlice: Towards Effective DNN Model Maintenance via Neuron-Level Semantic Slicing"],"prefix":"10.1145","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7891-8946","authenticated-orcid":false,"given":"Shide","family":"Zhou","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2207-1622","authenticated-orcid":false,"given":"Tianlin","family":"Li","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5784-770X","authenticated-orcid":false,"given":"Yihao","family":"Huang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2023-0247","authenticated-orcid":false,"given":"Ling","family":"Shi","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3977-6573","authenticated-orcid":false,"given":"Kailong","family":"Wang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7300-9215","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1100-8633","authenticated-orcid":false,"given":"Haoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,11]]},"reference":[{"key":"e_1_3_3_2_2","unstructured":"Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen Craig Citro Greg S. Corrado Andy Davis Jeffrey Dean Matthieu Devin et al. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Retrieved from https:\/\/www.tensorflow.org\/Software"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.031"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.5555\/794203.795290"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394112"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2022.3218005"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.327"},{"key":"e_1_3_3_8_2","doi-asserted-by":"crossref","unstructured":"Jia Deng Wei Dong Richard Socher Li-Jia Li Kai Li and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. IEEE 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3359786"},{"key":"e_1_3_3_10_2","first-page":"2943","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Evci Utku","year":"2020","unstructured":"Utku Evci, Trevor Gale, Jacob Menick, Pablo Samuel Castro, and Erich Elsen. 2020. Rigging the lottery: Making all tickets winners. In Proceedings of the 37th International Conference on Machine Learning. PMLR, 2943\u20132952. Retrieved from https:\/\/proceedings.mlr.press\/v119\/evci20a.html"},{"key":"e_1_3_3_11_2","unstructured":"Trevor Gale Erich Elsen and Sara Hooker. 2019. The state of sparsity in deep neural networks. arXiv:1902.09574. Retrieved from https:\/\/arxiv.org\/abs\/1902.09574"},{"key":"e_1_3_3_12_2","volume-title":"Proceedings of the 3rd International Conference on Learning Representations (ICLR \u201915)","author":"Goodfellow Ian J.","year":"2015","unstructured":"Ian J. Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and harnessing adversarial examples. In Proceedings of the 3rd International Conference on Learning Representations (ICLR \u201915). Retrieved from https:\/\/arxiv.org\/abs\/1412.6572"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"e_1_3_3_14_2","unstructured":"Andrew G. Howard Menglong Zhu Bo Chen Dmitry Kalenichenko Weijun Wang Tobias Weyand Marco Andreetto and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861. Retrieved from https:\/\/arxiv.org\/abs\/1704.04861"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3672454"},{"key":"e_1_3_3_16_2","unstructured":"Jonathan Ish-Horowicz Dana Udwin Seth R. Flaxman Sarah Filippi and Lorin Crawford. 2019. Interpreting deep neural networks through variable importance. arXiv:1901.09839. Retrieved from https:\/\/arxiv.org\/abs\/1901.09839"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630011"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/SCAM.2014.23"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3635706"},{"key":"e_1_3_3_20_2","unstructured":"Narine Kokhlikyan Vivek Miglani Miguel Martin Edward Wang Bilal Alsallakh Jonathan Reynolds Alexander Melnikov Natalia Kliushkina Carlos Araya Siqi Yan et al. 2020. Captum: A unified and generic model interpretability library for PyTorch. arXiv:2009.07896. Retrieved from https:\/\/arxiv.org\/abs\/2009.07896"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-017-0064-6"},{"key":"e_1_3_3_22_2","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1007\/3-540-47764-0_3","volume-title":"Static Analysis","author":"Komondoor Raghavan","year":"2001","unstructured":"Raghavan Komondoor and Susan Horwitz. 2001. Using slicing to identify duplication in source code. In Static Analysis. Patrick Cousot (Ed.). Springer Berlin, Berlin, 40\u201356."},{"key":"e_1_3_3_23_2","first-page":"3519","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Kornblith Simon","year":"2019","unstructured":"Simon Kornblith, Mohammad Norouzi, Honglak Lee, and Geoffrey Hinton. 2019. Similarity of neural network representations revisited. In Proceedings of the International Conference on Machine Learning. PMLR, 3519\u20133529."},{"key":"e_1_3_3_24_2","unstructured":"Alex Krizhevsky and Geoffrey Hinton. 2009. Learning multiple layers of features from tiny images. Retrieved from https:\/\/www.cs.utoronto.ca\/~kriz\/learning-features-2009-TR.pdf"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3688841"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_3_28_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Lee Jaeho","year":"2021","unstructured":"Jaeho Lee, Sejun Park, Sangwoo Mo, Sungsoo Ahn, and Jinwoo Shin. 2021. Layer-adaptive sparsity for the magnitude-based pruning. In Proceedings of the International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=H6ATjJ0TKdf"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3707453"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00073"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623334"},{"key":"e_1_3_3_32_2","first-page":"19471","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Li Tianlin","year":"2023","unstructured":"Tianlin Li, Qing Guo, Aishan Liu, Mengnan Du, Zhiming Li, and Yang Liu. 2023. FAIRER: Fairness as decision rationale alignment. In Proceedings of the International Conference on Machine Learning. PMLR, 19471\u201319489."},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.08.043"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3617168"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2017.8115722"},{"key":"e_1_3_3_36_2","unstructured":"Yanzhou Li Tianlin Li Kangjie Chen Jian Zhang Shangqing Liu Wenhan Wang Tianwei Zhang and Yang Liu. 2024. Badedit: Backdooring large language models by model editing. arXiv:2403.13355. Retrieved from https:\/\/arxiv.org\/abs\/2403.13355"},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3644387"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00470-5_13"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3078407"},{"key":"e_1_3_3_40_2","volume-title":"Proceedings of the 6th International Conference on Learning Representations (ICLR \u201918)","author":"Madry Aleksander","year":"2018","unstructured":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2018. Towards deep learning models resistant to adversarial attacks. In Proceedings of the 6th International Conference on Learning Representations (ICLR \u201918). OpenReview.net. Retrieved from https:\/\/openreview.net\/forum?id=rJzIBfZAb"},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"e_1_3_3_42_2","volume-title":"Advances in Neural Information Processing Systems","author":"Morcos Ari","year":"2019","unstructured":"Ari Morcos, Haonan Yu, Michela Paganini, and Yuandong Tian. 2019. One ticket to win them all: Generalizing lottery ticket initializations across datasets and optimizers. In Advances in Neural Information Processing Systems. H. Wallach, H. Larochelle, A. Beygelzimer, F. d\u2019Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32, Curran Associates, Inc. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/a4613e8d72a61b3b69b32d040f89ad81-Paper.pdf"},{"key":"e_1_3_3_43_2","unstructured":"NeuSemSlice. 2025. NeuSemSlice: Towards Effective DNN Model Maintenance via Neuron-level Semantic Slicing. Retrieved March 21 2025 from https:\/\/sites.google.com\/view\/neusemslice"},{"key":"e_1_3_3_44_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Nguyen Thao","year":"2021","unstructured":"Thao Nguyen, Maithra Raghu, and Simon Kornblith. 2021. Do wide and deep networks learn the same things? Uncovering how neural network representations vary with width and depth. In Proceedings of the International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=KJNcAkY8tY4"},{"key":"e_1_3_3_45_2","unstructured":"Nicolas Papernot Fartash Faghri Nicholas Carlini Ian Goodfellow Reuben Feinman Alexey Kurakin Cihang Xie Yash Sharma Tom Brown Aurko Roy et al. 2018. Technical report on the CleverHans v2.1.0 adversarial examples library. arXiv:1610.00768. Retrieved from https:\/\/arxiv.org\/abs\/1610.00768"},{"key":"e_1_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3639478.3643117"},{"key":"e_1_3_3_47_2","first-page":"8024","volume-title":"Advances in Neural Information Processing Systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. PyTorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems. Vol. 32. Curran Associates, Inc., 8024\u20138035. Retrieved from http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"e_1_3_3_48_2","first-page":"1","volume-title":"In Proceedings of the 26th Symposium on Operating Systems Principles","author":"Pei Kexin","year":"2017","unstructured":"Kexin Pei, Yinzhi Cao, Junfeng Yang, and Suman Jana. 2017. Deepxplore: Automated whitebox testing of deep learning systems. In Proceedings of the 26th Symposium on Operating Systems Principles, 1\u201318."},{"key":"e_1_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00092"},{"key":"e_1_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/2393596.2393646"},{"key":"e_1_3_3_51_2","first-page":"3145","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Shrikumar Avanti","year":"2017","unstructured":"Avanti Shrikumar, Peyton Greenside, and Anshul Kundaje. 2017. Learning important features through propagating activation differences. In Proceedings of the International Conference on Machine Learning. PMLR, 3145\u20133153."},{"key":"e_1_3_3_52_2","volume-title":"Proceedings of the 3rd International Conference on Learning Representations (ICLR \u201915)","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In Proceedings of the 3rd International Conference on Learning Representations (ICLR \u201915). Retrieved from https:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579640"},{"key":"e_1_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510080"},{"key":"e_1_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114632"},{"key":"e_1_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"key":"e_1_3_3_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367329"},{"key":"e_1_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3672446"},{"key":"e_1_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3604609"},{"key":"e_1_3_3_60_2","unstructured":"Han Xiao Kashif Rasul and Roland Vollgraf. 2017. Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms. arXiv:1708.07747. Retrieved from https:\/\/arxiv.org\/abs\/1708.07747"},{"key":"e_1_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3490489"},{"key":"e_1_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3042083"},{"key":"e_1_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409676"}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731556","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T15:56:33Z","timestamp":1765468593000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731556"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,11]]},"references-count":62,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,31]]}},"alternative-id":["10.1145\/3731556"],"URL":"https:\/\/doi.org\/10.1145\/3731556","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,11]]},"assertion":[{"value":"2024-07-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}