{"type":"ScholarlyArticle","title":"Machine Unlearning via Null Space Calibration","authors":[{"name":"Huiqiang Chen","slug":"huiqiang-chen","given":"Huiqiang","family":"Chen","affiliation":"University of Technology Sydney , NSW , Australia"},{"name":"Tianqing Zhu","slug":"tianqing-zhu","given":"Tianqing","family":"Zhu","affiliation":"City University of Macau , Macau , China"},{"name":"Xin Yu","slug":"xin-yu","given":"Xin","family":"Yu","affiliation":"University of Queensland , QLD , Australia"},{"name":"Wanlei Zhou","slug":"wanlei-zhou","given":"Wanlei","family":"Zhou","affiliation":"City University of Macau , Macau , China"}],"abstract":"Machine unlearning aims to enable models to forget specific data instances when receiving deletion requests. Current research centers on efficient unlearning to erase the influence of data from the model and neglects the subsequent impacts on the remaining data. Consequently, existing unlearning algorithms degrade the model's performance after unlearning, known as over-unlearning. This paper addresses this critical yet under-explored issue by introducing machine Unlearning via Null Space Calibration (UNSC), which can accurately unlearn target samples without over-unlearning. On the contrary, by calibrating the decision space during unlearning, UNSC can significantly improve the model's performance on the remaining samples. In particular, our approach hinges on confining the unlearning process to a specified null space tailored to the remaining samples, which is augmented by strategically pseudo-labeling the unlearning samples. Comparison against several established baselines affirms the superiority of our approach.","doi":"10.24963/ijcai.2024/40","url":"https://ijcai.org/proceedings/2024/40","pdf":"https://ijcai.org/proceedings/2024/0040.pdf","markdown":"https://ijcai.org/proceedings/2024/40.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/40","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"AI Ethics, Trust, Fairness","track":"Main Track","number":40,"pages":{"first":358,"last":366},"keywords":["AI Ethics, Trust, Fairness: ETF: Trustworthy AI","AI Ethics, Trust, Fairness: ETF: Accountability","AI Ethics, Trust, Fairness: ETF: Other","AI Ethics, Trust, Fairness: ETF: Ethical, legal and societal issues"],"videos":[],"references":[{"position":1,"raw":"[Allen-Zhu et al., 2019] Zeyuan Allen-Zhu, Yuanzhi Li, and Zhao Song. A convergence theory for deep learning via over-parameterization. In International conference on ma- chine learning, pages 242-252. PMLR, 2019.","title":"A convergence theory for deep learning via over-parameterization","authors":"Allen-Zhu","year":"2019","venue":"International conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bourtoule et al., 2021] Lucas Bourtoule, Varun Chan- drasekaran, Christopher Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, and Nicolas Papernot. Machine unlearning. In Proceedings of the 42nd IEEE Symposium on Security and Privacy, 2021.","title":"Machine unlearning","authors":"Lucas Bourtoule, Varun Chandrasekaran, Christopher Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, Nicolas Papernot","year":"2021","venue":"Proceedings of the 42nd IEEE Symposium on Security and Privacy","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cao and Yang, 2015] Yinzhi Cao and Junfeng Yang. To- wards making systems forget with machine unlearning. In 2015 IEEE symposium on security and privacy, pages 463-480. IEEE, 2015.","title":"Towards making systems forget with machine unlearning","authors":"Yang ; ] Yinzhi Cao, Junfeng Cao, Yang","year":"2015","venue":"IEEE symposium on security and privacy","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2023] Min Chen, Weizhuo Gao, Gaoyang Liu, Kai Peng, and Chen Wang. Boundary unlearning: Rapid forgetting of deep networks via shifting the decision boundary. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 7766-7775, June 2023.","title":"Boundary unlearning: Rapid forgetting of deep networks via shifting the decision boundary","authors":"Chen","year":"2023","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Fan et al., 2023] Chongyu Fan, Jiancheng Liu, Yihua Zhang, Dennis Wei, Eric Wong, and Sijia Liu. Salun: Em- powering machine unlearning via gradient-based weight saliency in both image classification and generation. arXiv preprint arXiv:2310.12508, 2023.","title":"Salun: Empowering machine unlearning via gradient-based weight saliency in both image classification and generation","authors":"Chongyu Fan, Jiancheng Liu, Yihua Zhang, Dennis Wei, Eric Wong, Sijia Liu","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Farajtabar et al., 2020] Mehrdad Farajtabar, Navid Azizan, Alex Mott, and Ang Li. Orthogonal gradient descent for continual learning. In International Conference on Artifi- cial Intelligence and Statistics, pages 3762-3773. PMLR, 2020.","title":"Orthogonal gradient descent for continual learning","authors":"Mehrdad Farajtabar, Navid Azizan, Alex Mott, Ang Li","year":"2020","venue":"International Conference on Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ginart et al., 2019] Antonio Ginart, Melody Guan, Gregory Valiant, and James Y Zou. Making ai forget you: Data deletion in machine learning. Advances in neural infor- mation processing systems, 32, 2019.","title":"Making ai forget you: Data deletion in machine learning","authors":"Ginart","year":"2019","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Golatkar et al., 2020] Aditya Golatkar, Alessandro Achille, and Stefano Soatto. Eternal sunshine of the spotless net: Selective forgetting in deep networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition, pages 9304-9312, 2020.","title":"Eternal sunshine of the spotless net: Selective forgetting in deep networks","authors":"Aditya Golatkar, Alessandro Achille, Stefano Soatto","year":"2020","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Graves et al., 2021] Laura Graves, Vineel Nagisetty, and Vijay Ganesh. Amnesiac machine learning. In Proceed- ings of the AAAI Conference on Artificial Intelligence, vol- ume 35, pages 11516-11524, 2021.","title":"Amnesiac machine learning","authors":"Laura Graves, Vineel Nagisetty, Vijay Ganesh","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Guo et al., 2019] Chuan Guo, Tom Goldstein, Awni Han- nun, and Laurens Van Der Maaten. Certified data re- moval from machine learning models. arXiv preprint arXiv:1911.03030, 2019.","title":"Certified data removal from machine learning models","authors":"Chuan Guo, Tom Goldstein, Awni Hannun, Laurens Van Der Maaten","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Gur-Ari et al., 2018] Guy Gur-Ari, Daniel A Roberts, and Ethan Dyer. Gradient descent happens in a tiny subspace. arXiv preprint arXiv:1812.04754, 2018.","title":"Gradient descent happens in a tiny subspace","authors":"Gur-Ari","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Hayase et al., 2020] Tomohiro Hayase, Suguru Yasutomi, and Takashi Katoh. Selective forgetting of deep net- works at a finer level than samples. arXiv preprint arXiv:2012.11849, 2020.","title":"Selective forgetting of deep networks at a finer level than samples","authors":"Tomohiro Hayase, Suguru Yasutomi, Takashi Katoh","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[He et al., 2015] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition, 2015.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Hoofnagle et al., 2019] Chris Jay Hoofnagle, Bart Van Der Sloot, and Frederik Zuiderveen Borgesius. The eu- ropean union general data protection regulation: what it is and what it means. Information & Communications Tech- nology Law, 28(1):65-98, 2019.","title":"The european union general data protection regulation: what it is and what it means","authors":"Chris Jay Hoofnagle, Bart Van Der, Frederik Zuiderveen Sloot, Borgesius","year":"2019","venue":"Information & Communications Technology Law","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Hu et al., 2023] Hongsheng Hu, Shuo Wang, Jiamin Chang, Haonan Zhong, Ruoxi Sun, Shuang Hao, Haojin Zhu, and Minhui Xue. A duty to forget, a right to be assured? expos- ing vulnerabilities in machine unlearning services. arXiv preprint arXiv:2309.08230, 2023.","title":"A duty to forget, a right to be assured? exposing vulnerabilities in machine unlearning services","authors":"Hongsheng Hu, Shuo Wang, Jiamin Chang, Haonan Zhong, Ruoxi Sun, Shuang Hao, Haojin Zhu, Minhui Xue","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Koh and Liang, 2017] Pang Wei Koh and Percy Liang. Un- derstanding black-box predictions via influence functions. In International conference on machine learning, pages 1885-1894. PMLR, 2017.","title":"Understanding black-box predictions via influence functions","authors":"Pang Wei, Koh, Percy Liang","year":"2017","venue":"International conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Krizhevsky et al., 2009] Alex Krizhevsky, Geoffrey Hinton, et al. Learning multiple layers of features from tiny im- ages. 2009.","title":"Learning multiple layers of features from tiny images","authors":"Alex Krizhevsky, Geoffrey Hinton","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Krizhevsky et al., 2012] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. Advances in neural infor- mation processing systems, 25, 2012.","title":"Imagenet classification with deep convolutional neural networks","authors":"Alex Krizhevsky, Ilya Sutskever, Geoffrey E Hinton","year":"2012","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Lee and Choi, 2018] Yoonho Lee and Seungjin Choi. Gradient-based meta-learning with learned layerwise met- ric and subspace. In International Conference on Machine Learning, pages 2927-2936. PMLR, 2018.","title":"Yoonho Lee and Seungjin Choi. Gradient-based meta-learning with learned layerwise metric and subspace","authors":"Choi Lee","year":"2018","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Li et al., 2018] Chunyuan Li, Heerad Farkhoor, Rosanne Liu, and Jason Yosinski. Measuring the intrinsic dimension of objective landscapes. arXiv preprint arXiv:1804.08838, 2018.","title":"Measuring the intrinsic dimension of objective landscapes","authors":"Chunyuan Li, Heerad Farkhoor, Rosanne Liu, Jason Yosinski","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Li et al., 2022] Tao Li, Lei Tan, Zhehao Huang, Qinghua Tao, Yipeng Liu, and Xiaolin Huang. Low dimensional trajectory hypothesis is true: Dnns can be trained in tiny subspaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(3):3411-3420, 2022.","title":"Low dimensional trajectory hypothesis is true: Dnns can be trained in tiny subspaces","authors":"Tao Li, Lei Tan, Zhehao Huang, Qinghua Tao, Yipeng Liu, Xiaolin Huang","year":"2022","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Li et al., 2023] Guanghao Li, Li Shen, Yan Sun, Yue Hu, Han Hu, and Dacheng Tao. Subspace based federated un- learning, 2023.","title":"Subspace based federated unlearning","authors":"Guanghao Li, Li Shen, Yan Sun, Yue Hu, Han Hu, Dacheng Tao","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Lin et al., 2023] Shen Lin, Xiaoyu Zhang, Chenyang Chen, Xiaofeng Chen, and Willy Susilo. Erm-ktp: Knowledge- level machine unlearning via knowledge transfer. In Pro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 20147-20155, 2023.","title":"Erm-ktp: Knowledgelevel machine unlearning via knowledge transfer","authors":"Xiaoyu Shen Lin, Chenyang Zhang, Xiaofeng Chen, Willy Chen, Susilo","year":"2023","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Liu et al., 2018] Zhenhua Liu, Jizheng Xu, Xiulian Peng, and Ruiqin Xiong. Frequency-domain dynamic pruning for convolutional neural networks. Advances in neural in- formation processing systems, 31, 2018.","title":"Frequency-domain dynamic pruning for convolutional neural networks","authors":"Zhenhua Liu, Jizheng Xu, Xiulian Peng, Ruiqin Xiong","year":"2018","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[McInnes et al., 2018] Leland McInnes, John Healy, and James Melville. Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426, 2018.","title":"Umap: Uniform manifold approximation and projection for dimension reduction","authors":"Leland Mcinnes, John Healy, James Melville","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Netzer et al., 2011] Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Baolin Wu, Andrew Y Ng, et al. Reading digits in natural images with unsupervised feature learning. In NIPS workshop on deep learning and unsu- pervised feature learning, volume 2011, page 7. Granada, Spain, 2011.","title":"Reading digits in natural images with unsupervised feature learning","authors":"Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Baolin Wu, Andrew Y Ng","year":"2011","venue":"NIPS workshop on deep learning and unsupervised feature learning","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Rosenfeld et al., 2020] Elan Rosenfeld, Ezra Winston, Pradeep Ravikumar, and Zico Kolter. Certified robust- ness to label-flipping attacks via randomized smoothing. In International Conference on Machine Learning, pages 8230-8241. PMLR, 2020.","title":"Certified robustness to label-flipping attacks via randomized smoothing","authors":"Rosenfeld","year":"2020","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Saha et al., 2021] Gobinda Saha, Isha Garg, and Kaushik Roy. Gradient projection memory for continual learning. arXiv preprint arXiv:2103.09762, 2021.","title":"Gradient projection memory for continual learning","authors":"Gobinda Saha, Isha Garg, Kaushik Roy","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Shokri et al., 2017] Reza Shokri, Marco Stronati, Con- gzheng Song, and Vitaly Shmatikov. Membership infer- ence attacks against machine learning models, 2017.","title":"Membership inference attacks against machine learning models","authors":"Reza Shokri, Marco Stronati, Congzheng Song, Vitaly Shmatikov","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Simonyan and Zisserman, 2015] Karen Simonyan and An- drew Zisserman. Very deep convolutional networks for large-scale image recognition, 2015.","title":"Very deep convolutional networks for large-scale image recognition","authors":"Karen Simonyan, Andrew Zisserman","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Springenberg et al., 2015] Jost Tobias Springenberg, Alexey Dosovitskiy, Thomas Brox, and Martin Ried- miller. Striving for simplicity: The all convolutional net, 2015.","title":"Striving for simplicity: The all convolutional net","authors":"Jost Tobias Springenberg, Alexey Dosovitskiy, Thomas Brox, Martin Riedmiller","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Xiao et al., 2017] Han Xiao, Kashif Rasul, and Roland Vollgraf. Fashion-mnist: a novel image dataset for bench- marking machine learning algorithms. arXiv preprint arXiv:1708.07747, 2017.","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms","authors":"Han Xiao, Kashif Rasul, Roland Vollgraf","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Xu et al., 2023] Heng Xu, Tianqing Zhu, Lefeng Zhang, Wanlei Zhou, and Philip S Yu. Machine unlearning: A survey. ACM Computing Surveys, 56(1):1-36, 2023.","title":"Machine unlearning: A survey","authors":"Heng Xu, Tianqing Zhu, Lefeng Zhang, Wanlei Zhou, Philip S Yu","year":"2023","venue":"ACM Computing Surveys","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}