{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:15:30Z","timestamp":1758672930994,"version":"3.44.0"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:p>As machine learning models become widely deployed in data-driven applications, ensuring compliance with the 'right to be forgotten' as required by many privacy regulations is vital for safeguarding user privacy. To forget the given data, existing re-labeling based unlearning methods employ a single-step adjustment scheme that revises the decision boundaries in one re-labeling phase. However, such single-step approaches lead to coarse-grained changes in decision boundaries among the remaining classes and impose adverse effects on the model utility. To address these limitations, we propose 'Self-Unlearning with Layered Iteration (SULI),' a novel unlearning approach that introduces a layered iteration strategy to re-label the forgetting data iteratively and refine the decision boundaries progressively. We further develop a 'Selective Probability Adjustment (SPA)' technique, which uses a soft-label mechanism to promote smoother decision-boundary transitions. Comprehensive experiments on three benchmark datasets demonstrate that SULI achieves superior performance in effectiveness, efficiency, and privacy compared to the state-of-the-art baselines in both class-wise and instance-wise unlearning scenarios. The source code is released at https:\/\/github.com\/Hongyi-Lyu-MQ\/SULI.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/850","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"7643-7651","source":"Crossref","is-referenced-by-count":0,"title":["Fine-Grained and Efficient Self-Unlearning with Layered Iteration"],"prefix":"10.24963","author":[{"given":"Hongyi","family":"Lyu","sequence":"first","affiliation":[{"name":"Macquarie University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuyun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Macquarie University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongsheng","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Newcastle"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoxiang","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lianyong","family":"Qi","sequence":"additional","affiliation":[{"name":"China University of Petroleum (East China)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"34","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2025","name":"Thirty-Fourth International Joint Conference on Artificial Intelligence {IJCAI-25}","start":{"date-parts":[[2025,8,16]]},"theme":"Artificial Intelligence","location":"Montreal, Canada","end":{"date-parts":[[2025,8,22]]}},"container-title":["Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T11:35:18Z","timestamp":1758627318000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/850"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2025\/850","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}