{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T15:32:05Z","timestamp":1773588725761,"version":"3.50.1"},"reference-count":62,"publisher":"Association for Computing Machinery (ACM)","issue":"1","funder":[{"name":"Project of Guangxi Science and Technology","award":["GuiKeAB23026040"],"award-info":[{"award-number":["GuiKeAB23026040"]}]},{"name":"Research Fund of Guangxi Key Lab of Multi-source Information Mining & Security","award":["MIMS24-13, 24-A-01-02, and MIMS24-03"],"award-info":[{"award-number":["MIMS24-13, 24-A-01-02, and MIMS24-03"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Auton. Adapt. Syst."],"published-print":{"date-parts":[[2026,3,31]]},"abstract":"<jats:p>\n                    Graph unlearning system offers a promising solution for securely erasing specific data points and their associated influences from Graph Neural Networks (GNNs). However, existing approaches often treat the problem as multiple isolated and disjoint sub-problems by partitioning graph data into isolated subgraphs, which overlooks the native graph structure information between subgraphs. This results in biased representations that hinder the accurate modeling of key connections and relationships within the data, leading to a notable reduction in model utility due to this loss of information. To address these issues, we propose an innovative framework called\n                    <jats:italic toggle=\"yes\">N<\/jats:italic>\n                    on-\n                    <jats:italic toggle=\"yes\">I<\/jats:italic>\n                    solated\n                    <jats:italic toggle=\"yes\">G<\/jats:italic>\n                    raph\n                    <jats:italic toggle=\"yes\">Eraser<\/jats:italic>\n                    (NIGEraser) that decomposes the unlearning task into multiple non-isolated, intersecting sub-problems. Specifically, a novel non-isolated graph partitioning strategy is proposed for NIGEraser that mitigates isolation by replicating key nodes across multiple neighboring subgraphs, along with an attention-based sub-model aggregation technique in that global graph structure information is employed. By this design, a broader natural neighborhood is explored, capturing and effectively utilizing the critical graph structure features lost between subgraphs during partitioning, thereby reducing information loss during task decomposition and aggregation. Additionally, it is demonstrated that graph unlearning methods can overcome the limitations of traditional isolated partitioning strategies, providing an effective theoretical constraint on time consumption. Extensive experiments on four real-world graph-structured datasets show that NIGEraser consistently outperforms existing unlearning methods, offering superior model utility while ensuring efficient and deterministic data removal.\n                  <\/jats:p>","DOI":"10.1145\/3750734","type":"journal-article","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T17:12:41Z","timestamp":1753377161000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Graph Unlearning System with Subgraph De-Isolation Measures"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2052-3399","authenticated-orcid":false,"given":"Yi","family":"Li","sequence":"first","affiliation":[{"name":"Guangxi Normal University, Guilin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0383-1462","authenticated-orcid":false,"given":"Debo","family":"Cheng","sequence":"additional","affiliation":[{"name":"University of South Australia, Adelaide, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7632-8411","authenticated-orcid":false,"given":"Guixian","family":"Zhang","sequence":"additional","affiliation":[{"name":"China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3528-1036","authenticated-orcid":false,"given":"Chengyu","family":"Li","sequence":"additional","affiliation":[{"name":"Guangxi Normal University, Guilin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9981-2970","authenticated-orcid":false,"given":"Shichao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Guangxi Normal University, Guilin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.3390\/s21144758"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/1671948.1671952"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1080\/15427951.2005.10129098"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00019"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2015.35"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833649"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511997"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3641283"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3559352"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3265506"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313799"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3450528"},{"issue":"8","key":"e_1_3_2_14_2","first-page":"7665","article-title":"A multi-view multi-task learning framework for multi-variate time series forecasting","volume":"35","author":"Deng Jinliang","year":"2022","unstructured":"Jinliang Deng, Xiusi Chen, Renhe Jiang, Xuan Song, and Ivor W. Tsang. 2022. A multi-view multi-task learning framework for multi-variate time series forecasting. IEEE Transactions on Knowledge and Data Engineering 35, 8 (2022), 7665\u20137680.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3371931"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3605894"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-019-8208-z"},{"key":"e_1_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Daniel L. Felps Amelia D. Schwickerath Joyce D. Williams Trung N. Vuong Alan Briggs Matthew Hunt Evan Sakmar David D. Saranchak and Tyler Shumaker. 2020. Class Clown: Data redaction in machine unlearning at enterprise scale. arXiv:2012.04699. Retrieved from https:\/\/arxiv.org\/abs\/2012.04699","DOI":"10.5220\/0010419600002859"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3469440"},{"key":"e_1_3_2_20_2","unstructured":"Chuan Guo Tom Goldstein Awni Hannun and Laurens Van Der Maaten. 2019. Certified data removal from machine learning models. arXiv:1911.03030. Retrieved from https:\/\/arxiv.org\/abs\/1911.03030"},{"key":"e_1_3_2_21_2","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 30.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_22_2","unstructured":"Yingzhe He Guozhu Meng Kai Chen Jinwen He and Xingbo Hu. 2021. DeepObliviate: A powerful charm for erasing data residual memory in deep neural networks. arXiv:2105.06209. Retrieved from https:\/\/arxiv.org\/abs\/2105.06209"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611977172.20"},{"key":"e_1_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Zhirong Huang Shichao Zhang Debo Cheng Jiuyong Li Lin Liu and Guangquan Lu. 2024. Data-driven conditional instrumental variables for debiasing recommender systems. arXiv:2408.09651. Retrieved from https:\/\/arxiv.org\/abs\/2408.09651","DOI":"10.24963\/ijcai.2024\/329"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017616"},{"key":"e_1_3_2_26_2","unstructured":"Thomas N. Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv:1609.02907. Retrieved from https:\/\/arxiv.org\/abs\/1609.02907"},{"key":"e_1_3_2_27_2","unstructured":"Thomas N. Kipf and Max Welling. 2016. Variational graph auto-encoders. arXiv:1611.07308. Retrieved from https:\/\/arxiv.org\/abs\/1611.07308"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0018961"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3649453"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3708353"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3345251"},{"key":"e_1_3_2_32_2","first-page":"1","article-title":"EduGraph: Learning path-based hypergraph neural networks for MOOC course recommendation","author":"Li Ming","year":"2024","unstructured":"Ming Li, Zhao Li, Changqin Huang, Yunliang Jiang, and Xindong Wu. 2024. EduGraph: Learning path-based hypergraph neural networks for MOOC course recommendation. IEEE Transactions on Big Data 01 (2024), 1\u201315.","journal-title":"IEEE Transactions on Big Data"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111340"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102428"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i17.34041"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-020-3437-6"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.clsr.2013.03.010"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3268069"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.clsr.2018.08.006"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3638549"},{"key":"e_1_3_2_41_2","unstructured":"Oleksandr Shchur Maximilian Mumme Aleksandar Bojchevski and Stephan G\u00fcnnemann. 2018. Pitfalls of graph neural network evaluation. arXiv:1811.05868. Retrieved from https:\/\/arxiv.org\/abs\/1811.05868"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/2821512"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3266233"},{"key":"e_1_3_2_44_2","unstructured":"Petar Veli\u010dkovi\u0107 Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Lio and Yoshua Bengio. 2017. Graph attention networks. arXiv:1710.10903. Retrieved from https:\/\/arxiv.org\/abs\/1710.10903"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.5555\/3620237.3620417"},{"key":"e_1_3_2_46_2","first-page":"515","volume-title":"Proceedings of the 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201921)","author":"Wang Yuke","year":"2021","unstructured":"Yuke Wang, Boyuan Feng, Gushu Li, Shuangchen Li, Lei Deng, Yuan Xie, and Yufei Ding. 2021. GNNAdvisor: An adaptive and efficient runtime system for GNN acceleration on GPUs. In Proceedings of the 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201921), 515\u2013531."},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052575"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974010.105"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM51629.2021.00182"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330950"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583521"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2011.154"},{"issue":"1","key":"e_1_3_2_53_2","first-page":"1","article-title":"Machine unlearning: A survey","volume":"56","author":"Xu Heng","year":"2023","unstructured":"Heng Xu, Tianqing Zhu, Lefeng Zhang, Wanlei Zhou, and Philip S. Yu. 2023. Machine unlearning: A survey. ACM Computing Surveys 56, 1 (2023), 1\u201336.","journal-title":"ACM Computing Surveys"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCC50000.2020.9219587"},{"key":"e_1_3_2_55_2","first-page":"40","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Yang Zhilin","year":"2016","unstructured":"Zhilin Yang, William Cohen, and Ruslan Salakhudinov. 2016. Revisiting semi-supervised learning with graph embeddings. In Proceedings of the International Conference on Machine Learning. PMLR, 40\u201348."},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103570"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109486"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3639408"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548378"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-009-0207-6"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.09.036"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3119140"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.06.082"}],"container-title":["ACM Transactions on Autonomous and Adaptive Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3750734","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T14:10:38Z","timestamp":1773583838000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3750734"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,10]]},"references-count":62,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,3,31]]}},"alternative-id":["10.1145\/3750734"],"URL":"https:\/\/doi.org\/10.1145\/3750734","relation":{},"ISSN":["1556-4665","1556-4703"],"issn-type":[{"value":"1556-4665","type":"print"},{"value":"1556-4703","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,10]]},"assertion":[{"value":"2024-12-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-19","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}