{"type":"ScholarlyArticle","title":"Machine Unlearning: Challenges in Data Quality and Access","authors":[{"name":"Miao Xu","slug":"miao-xu","given":"Miao","family":"Xu","affiliation":"School of Electrical Engineering and Computer Science , University of Queensland , Brisbane , Australia"}],"abstract":"Machine unlearning aims to remove specific knowledge from a well-trained machine learning model. This topic has gained significant attention recently due to the widespread adoption of machine learning models across various applications and the accompanying privacy, legal, and ethical considerations. During the unlearning process, models are typically presented with data that specifies which information should be erased and which should be retained. Nonetheless, practical challenges arise due to prevalent issues of data quality issues and access restrictions. This paper explores these challenges and introduces strategies to address problems related to unsupervised data, weakly supervised data, and scenarios characterized by zero-shot and federated data availability. Finally, we discuss related open questions, particularly concerning evaluation metrics, how the forgetting information is represented and delivered, and the unique challenges posed by large generative models.","doi":"10.24963/ijcai.2024/987","url":"https://ijcai.org/proceedings/2024/987","pdf":"https://ijcai.org/proceedings/2024/0987.pdf","markdown":"https://ijcai.org/proceedings/2024/987.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/987","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":"Early Career","track":"Early Career","number":987,"pages":{"first":8589,"last":8594},"keywords":["Machine Learning: ML: Weakly supervised learning","Machine Learning: ML: Trustworthy machine learning"],"videos":[],"references":[{"position":1,"raw":"[Bourtoule et al., 2021] Lucas Bourtoule, Varun Chan- drasekaran, Christopher A Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, and Nicolas Papernot. Machine unlearning. In Proceedings of the IEEE Symposium on Security and Privacy (SP), pages 141-159, 2021.","title":"Machine unlearning","authors":"Lucas Bourtoule, Varun Chandrasekaran, Christopher A Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, Nicolas Papernot","year":"2021","venue":"Proceedings of the IEEE Symposium on Security and Privacy (SP)","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Cao et al., 2023] Xiaoyu Cao, Jinyuan Jia, Zaixi Zhang, and Neil Zhenqiang Gong. Fedrecover: Recovering from poi- soning attacks in federated learning using historical infor- mation. In Proceedings of the IEEE Symposium on Secu- rity and Privacy (SP), pages 1366-1383, 2023.","title":"Fedrecover: Recovering from poisoning attacks in federated learning using historical information","authors":"Xiaoyu Cao, Jinyuan Jia, Zaixi Zhang, Neil Zhenqiang, Gong","year":"2023","venue":"Proceedings of the IEEE Symposium on Security and Privacy (SP)","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cesa-Bianchi and Lugosi, 2006] Nicolò Cesa-Bianchi and Gábor Lugosi. Prediction, learning, and games. Cam- bridge University Press, 2006.","title":"Nicolò Cesa-Bianchi and Gábor Lugosi","authors":"Cesa-Bianchi, Lugosi","year":"2006","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chang et al., 2024] Wenhan Chang, Tianqing Zhu, Heng Xu, Wenjian Liu, and Wanlei Zhou. Class machine un- learning for complex data via concepts inference and data poisoning. arXiv preprint arXiv:2405.15662, 2024.","title":"Class machine unlearning for complex data via concepts inference and data poisoning","authors":"Chang","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Che et al., 2023] Tianshi Che, Yang Zhou, Zijie Zhang, Lingjuan Lyu, Ji Liu, Da Yan, Dejing Dou, and Jun Huan. Fast federated machine unlearning with nonlinear func- tional theory. In Proceedings of the International Con- ference on Machine Learning (ICML), pages 4241-4268, 2023.","title":"Fast federated machine unlearning with nonlinear functional theory","authors":"Tianshi Che, Yang Zhou, Zijie Zhang, Lingjuan Lyu, Ji Liu, Da Yan, Dejing Dou, Jun Huan","year":"2023","venue":"Proceedings of the International Conference on Machine Learning (ICML)","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chundawat et al., 2023a] V. S. Chundawat, A. K. Tarun, M. Mandal, and M. S. Kankanhalli. Zero-shot machine unlearning. IEEE Transactions on Information Forensics and Security, pages 2345-2354, 2023.","title":"Zero-shot machine unlearning","authors":"Chundawat","year":"2023","venue":"IEEE Transactions on Information Forensics and Security","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chundawat et al., 2023b] Vikram S. Chundawat, Ayush K. Tarun, Murari Mandal, and Mohan S. Kankanhalli. Can bad teaching induce forgetting? unlearning in deep net- works using an incompetent teacher. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pages 7210-7217, 2023.","title":"Can bad teaching induce forgetting? unlearning in deep networks using an incompetent teacher","authors":"Chundawat","year":"2023","venue":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[de la Torre, 2018] Lydia de la Torre. A guide to the califor- nia consumer privacy act of 2018. SSRN 3275571, 2018.","title":"Lydia de la Torre. A guide to the california consumer privacy act of 2018","authors":"Torre De La","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Di et al., 2023] Jimmy Z. Di, Jack Douglas, Jayadev Acharya, Gautam Kamath, and Ayush Sekhari. Hidden poison: Machine unlearning enables camouflaged poison- ing attacks. In Advances in Neural Information Processing Systems (NeurIPS), 2023.","title":"Hidden poison: Machine unlearning enables camouflaged poisoning attacks","authors":"Jimmy Z Di, Jack Douglas, Jayadev Acharya, Gautam Kamath, Ayush Sekhari","year":"2023","venue":"Advances in Neural Information Processing Systems (NeurIPS)","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Fraboni et al., 2024] Yann Fraboni, Martin Van Waerebeke, Kevin Scaman, Richard Vidal, Laetitia Kameni, and Marco Lorenzi. Sifu: Sequential informed federated un- learning for efficient and provable client unlearning in fed- erated optimization. In Proceedings of the International Conference on Artificial Intelligence and Statistics (AIS- TATS), pages 3457-3465, 2024.","title":"Sifu: Sequential informed federated unlearning for efficient and provable client unlearning in federated optimization","authors":"Yann Fraboni, Martin Van Waerebeke, Kevin Scaman, Richard Vidal, Laetitia Kameni, Marco Lorenzi","year":"2024","venue":"Proceedings of the International Conference on Artificial Intelligence and Statistics (AIS-TATS)","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Gao et al., 2023] Yi Gao, Miao Xu, and Min-Ling Zhang. Unbiased risk estimator to multi-labeled complementary label learning. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pages 3732- 3740, 2023.","title":"Unbiased risk estimator to multi-labeled complementary label learning","authors":"Yi Gao, Miao Xu, Min-Ling Zhang","year":"2023","venue":"Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI)","doi":null,"url":null,"internal_url":"/proceedings/2023/415"},{"position":12,"raw":"[Gao et al., 2024] Xiangshan Gao, Xingjun Ma, Jingyi Wang, Youcheng Sun, Bo Li, Shouling Ji, Peng Cheng, and Jiming Chen. Verifi: Towards verifiable federated un- learning. IEEE Transactions on Dependable and Secure Computing, page PrePrints, 2024.","title":"Verifi: Towards verifiable federated unlearning","authors":"Gao","year":"2024","venue":"IEEE Transactions on Dependable and Secure Computing","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Halimi et al., 2022] Anisa Halimi, Swanand Kadhe, Ambr- ish Rawat, and Nathalie Baracaldo. Federated unlearn- ing: How to efficiently erase a client in fl? arXiv preprint arXiv:2207.05521, 2022.","title":"Federated unlearning: How to efficiently erase a client in fl","authors":"Anisa Halimi, Swanand Kadhe, Ambrish Rawat, Nathalie Baracaldo","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Han et al., 2018] Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor Tsang, and Masashi Sugiyama. Co-teaching: Robust training of deep neural networks with extremely noisy labels. Advances in Neu- ral Information Processing Systems (NeurIPS), 31:8536- 8546, 2018.","title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","authors":"Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor Tsang, Masashi Sugiyama","year":"2018","venue":"Advances in Neural Information Processing Systems (NeurIPS)","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Jin et al., 2023] Ruinan Jin, Minghui Chen, Qiong Zhang, and Xiaoxiao Li. Forgettable federated linear learning with certified data removal. arXiv preprint arXiv:2306.02216, 2023.","title":"Forgettable federated linear learning with certified data removal","authors":"Jin","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Kingma and Welling, 2014] Diederik P. Kingma and Max Welling. Auto-encoding variational bayes. In Interna- tional Conference on Learning Representations (ICLR), 2014.","title":"Auto-encoding variational bayes","authors":"P Diederik, Max Kingma, Welling","year":"2014","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"Konečný et al., ] Jakub Konečný, H. Brendan McMahan, Felix X. Yu, Peter Richtárik, Ananda Theertha Suresh, and Dave Bacon. Federated learning: Strategies for improving communication efficiency. arXiv preprint arXiv:1610.05492.","title":"Federated learning: Strategies for improving communication efficiency","authors":"Konečný","year":null,"venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Kurmanji et al., 2023] Meghdad Kurmanji, Peter Triantafil- lou, Jamie Hayes, and Eleni Triantafillou. Towards un- bounded machine unlearning. In Advances in Neural In- formation Processing Systems (NeurIPS), 2023.","title":"Towards unbounded machine unlearning","authors":"Kurmanji","year":"2023","venue":"Advances in Neural Information Processing Systems (NeurIPS)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Kwak et al., 2017] Chanhee Kwak, Junyeong Lee, Kyuhong Park, and Heeseok Lee. Let machines un- learn -machine unlearning and the right to be forgotten. In Americas Conference on Information Systems (AMCIS), 2017.","title":"Let machines unlearn -machine unlearning and the right to be forgotten","authors":"Kwak","year":"2017","venue":"Americas Conference on Information Systems (AMCIS)","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Liu et al., 2021] Gaoyang Liu, Xiaoqiang Ma, Yang Yang, Chen Wang, and Jiangchuan Liu. Federaser: Enabling efficient client-level data removal from federated learning models. In IEEE/ACM International Symposium on Qual- ity of Service (IWQOS), pages 1-10, 2021.","title":"Federaser: Enabling efficient client-level data removal from federated learning models","authors":"Gaoyang Liu, Xiaoqiang Ma, Yang Yang, Chen Wang, Jiangchuan Liu","year":"2021","venue":"IEEE/ACM International Symposium on Quality of Service (IWQOS)","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Liu et al., 2022] Yi Liu, Lei Xu, Xingliang Yuan, Cong Wang, and Bo Li. The right to be forgotten in federated learning: An efficient realization with rapid retraining. In IEEE Conference on Computer Communications (INFO- COM), pages 1749-1758, 2022.","title":"The right to be forgotten in federated learning: An efficient realization with rapid retraining","authors":"Yi Liu, Lei Xu, Xingliang Yuan, Cong Wang, Bo Li","year":"2022","venue":"IEEE Conference on Computer Communications (INFO-COM)","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Liu et al., 2023] Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM Computing Surveys, 55(9):195:1-195:35, 2023.","title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","authors":"Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, Graham Neubig","year":"2023","venue":"ACM Computing Surveys","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Liu et al., 2024] Sijia Liu, Yuanshun Yao, Jinghan Jia, Stephen Casper, Nathalie Baracaldo, Peter Hase, Xiaojun Xu, Yuguang Yao, Hang Li, Kush R Varshney, et al. Re- thinking machine unlearning for large language models. arXiv preprint arXiv:2402.08787, 2024.","title":"Rethinking machine unlearning for large language models","authors":"Sijia Liu, Yuanshun Yao, Jinghan Jia, Stephen Casper, Nathalie Baracaldo, Peter Hase, Xiaojun Xu, Yuguang Yao, Hang Li, R Kush, Varshney","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Lv et al., 2024] Jiaqi Lv, Biao Liu, Lei Feng, Ning Xu, Miao Xu, Bo An, Gang Niu, Xin Geng, and Masashi Sugiyama. On the robustness of average losses for partial- label learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(5):2569-2583, 2024.","title":"On the robustness of average losses for partiallabel learning","authors":"Jiaqi Lv, Biao Liu, Lei Feng, Ning Xu, Miao Xu, Bo An, Gang Niu, Xin Geng, Masashi Sugiyama","year":"2024","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Nguyen et al., 2022] Thanh Tam Nguyen, Thanh Trung Huynh, Phi Le Nguyen, Alan Wee-Chung Liew, Hongzhi Yin, and Quoc Viet Hung Nguyen. A survey of machine unlearning. arXiv preprint arXiv:2209.02299, 2022.","title":"A survey of machine unlearning","authors":"Thanh Tam Nguyen, Thanh Trung Huynh, Phi Le Nguyen, Alan Wee-Chung Liew, Hongzhi Yin, Quoc Viet, Hung Nguyen","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Romera-Paredes and Torr, 2015] Bernardino Romera- Paredes and Philip Torr. An embarrassingly simple approach to zero-shot learning. In Proceedings of the International Conference on Machine Learning (ICML), pages 2152-2161, 2015.","title":"Bernardino Romera-Paredes and Philip Torr. An embarrassingly simple approach to zero-shot learning","authors":"Romera-Paredes, Torr","year":"2015","venue":"Proceedings of the International Conference on Machine Learning (ICML)","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Shen et al., 2024a] Shaofei Shen, Chenhao Zhang, Alina Bialkowski, Weitong Chen, and Miao Xu. Camu: Disen- tangling causal effects in deep model unlearning. In Pro- ceedings of the SIAM Conference on Data Mining (SDM), 2024.","title":"Camu: Disentangling causal effects in deep model unlearning","authors":"Shen","year":"2024","venue":"Proceedings of the SIAM Conference on Data Mining (SDM)","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Shen et al., 2024b] Shaofei Shen, Chenhao Zhang, Yawen Zhao, Alina Bialkowski, Tony Weitong Chen, and Miao Xu. Label-agnostic forgetting: A supervision-free un- learning in deep models. In International Conference on Learning Representations (ICLR), 2024.","title":"Label-agnostic forgetting: A supervision-free unlearning in deep models","authors":"Shen","year":"2024","venue":"International Conference on Learning Representations (ICLR)","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. In Proceed- ings of the IEEE Symposium on Security and Privacy (SP), pages 3-18, 2017.","title":"Membership inference attacks against machine learning models","authors":"Reza Shokri, Marco Stronati, Congzheng Song, Vitaly Shmatikov","year":"2017","venue":"Proceedings of the IEEE Symposium on Security and Privacy (SP)","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Su et al., 2021] Guangxin Su, Weitong Chen, and Miao Xu. Positive-unlabeled learning from imbalanced data. In Pro- ceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pages 2995-3001, 2021.","title":"Positive-unlabeled learning from imbalanced data","authors":"Su","year":"2021","venue":"Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI)","doi":null,"url":null,"internal_url":"/proceedings/2021/412"},{"position":31,"raw":"[Tang et al., 2024] Yi Tang, Yi Gao, Yong-Gang Luo, Ju- Cheng Yang, Miao Xu, and Min-Ling Zhang. Unlearning from weakly supervised learning. In Proceedings of the In- ternational Joint Conference on Artificial Intelligence (IJ- CAI), 2024.","title":"Unlearning from weakly supervised learning","authors":"Yi Tang, Yi Gao, Yong-Gang Luo, Ju-Cheng Yang, Miao Xu, Min-Ling Zhang","year":"2024","venue":"Proceedings of the International Joint Conference on Artificial Intelligence (IJ-CAI)","doi":null,"url":null,"internal_url":"/proceedings/2024/553"},{"position":32,"raw":"[Tarun et al., 2021] Ayush K. Tarun, Vikram S. Chun- dawat, Murari Mandal, and Mohan S. Kankanhalli. Fast yet effective machine unlearning. arXiv preprint arXiv:2111.08947, 2021.","title":"Fast yet effective machine unlearning","authors":"K Ayush, Tarun, S Vikram, Murari Chundawat, Mohan S Mandal, Kankanhalli","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Thudi et al., 2022] Anvith Thudi, Gabriel Deza, Varun Chandrasekaran, and Nicolas Papernot. Unrolling SGD: understanding factors influencing machine unlearning. In IEEE European Symposium on Security and Privacy (Eu- roSP), pages 303-319, 2022.","title":"Unrolling SGD: understanding factors influencing machine unlearning","authors":"Thudi","year":"2022","venue":"IEEE European Symposium on Security and Privacy (Eu-roSP)","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Voigt and Von dem Bussche, 2017] Paul Voigt and Axel Von dem Bussche. The eu general data protection regula- tion (GDPR). A Practical Guide, 1st Ed., Cham: Springer International Publishing, 2017.","title":"The eu general data protection regulation (GDPR). A Practical Guide","authors":"Von Voigt, Dem Bussche","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Wang et al., 2022] Junxiao Wang, Song Guo, Xin Xie, and Heng Qi. Federated unlearning via class-discriminative pruning. In Proceedings of the ACM Web Conference (WWW), pages 622-632, 2022.","title":"Federated unlearning via class-discriminative pruning","authors":"Wang","year":"2022","venue":"Proceedings of the ACM Web Conference (WWW)","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Xiong et al., 2023] Zuobin Xiong, Wei Li, Yingshu Li, and Zhipeng Cai. Exact-fun: An exact and efficient federated unlearning approach. In IEEE International Conference on Data Mining (ICDM), pages 1439-1444, 2023.","title":"Exact-fun: An exact and efficient federated unlearning approach","authors":"Xiong","year":"2023","venue":"IEEE International Conference on Data Mining (ICDM)","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Xu et al., 2020] Miao Xu, Yufeng Li, and Zhi-Hua Zhou. Robust multi-label learning with PRO loss. IEEE Trans- actions on Knowledge and Data Engineering, 32(8):1610- 1624, 2020.","title":"Robust multi-label learning with PRO loss","authors":"Miao Xu, Yufeng Li, Zhi-Hua Zhou","year":"2020","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Xu et al., 2024] Heng Xu, Tianqing Zhu, Lefeng Zhang, Wanlei Zhou, and Philip S. Yu. Machine unlearning: A survey. ACM Computing Surveys, 56(1):9:1-9:36, 2024.","title":"Machine unlearning: A survey","authors":"Heng Xu, Tianqing Zhu, Lefeng Zhang, Wanlei Zhou, Philip S Yu","year":"2024","venue":"ACM Computing Surveys","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Zhang et al., 2022] Peng-Fei Zhang, Guangdong Bai, Zi Huang, and Xin-Shun Xu. Machine unlearning for image retrieval: A generative scrubbing approach. In ACM International Conference on Multimedia (MM), pages 237-245, 2022.","title":"Machine unlearning for image retrieval: A generative scrubbing approach","authors":"Peng-Fei Zhang, Guangdong Bai, Zi Huang, Xin-Shun Xu","year":"2022","venue":"ACM International Conference on Multimedia (MM)","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Zhang et al., 2024] Chenhao Zhang, Shaofei Shen, Yawen Zhao, Weitong Tony Chen, and Miao Xu. Geniu: A re- stricted data access unlearning for imbalanced data. arXiv preprint arXiv:2406.07885, 2024.","title":"Geniu: A restricted data access unlearning for imbalanced data","authors":"Zhang","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Zhou, 2018] Zhi-Hua Zhou. A brief introduction to weakly supervised learning. National science review, 5(1):44-53, 2018.","title":"A brief introduction to weakly supervised learning","authors":"Zhi-Hua Zhou","year":"2018","venue":"National science review","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}