2022

A Survey of Machine Unlearning

Nguyen, Thanh Tam, Huynh, Thanh Trung, Ren, Zhao et al.

Understand

Today, computer systems hold large amounts of personal data.

Yet while such an abundance of data allows breakthroughs in artificial intelligence, and especially machine learning (ML), its existence can be a threat to user privacy, and it can weaken the bonds of trust between humans and AI.
Recent regulations now require that, on request, private information about a user must be removed from both computer systems and from ML models, i.e.
``the right to be forgotten'').

Built on

On Information and Sufficiency
S. Kullback et al · 1951
Earlier work this paper cites.
Efficient noise-tolerant learning from statistical queries
Michael Kearns. 1998 · 1998
Earlier work this paper cites.
Incremental and decremental support vector machine learning
Gert Cauwenberghs et al · 2000
Earlier work this paper cites.
The information bottleneck method
Naftali Tishby et al · 2000
Earlier work this paper cites.
Extremely randomized trees
Pierre Geurts, Damien Ernst, et al · 2006
Earlier work this paper cites.
Decremental learning algorithms for nonlinear langrangian and least squares support vector machines. In OSB . 358–366
Hua Duan, Hua Li, Guoping He, and Qingtian Zeng. 2007 · 2007
Earlier work this paper cites.
Incremental and decremental learning for linear support vector machines. In ICANN . 209–218
Enrique Romero, Ignacio Barrio, and Lluís Belanche. 2007 · 2007
Earlier work this paper cites.
Differential privacy: A survey of results. In TAMC . 1–19
Cynthia Dwork. 2008 · 2008
Earlier work this paper cites.
Imagenet: A large-scale hierarchical image database. In CVPR . 248–255
Jia Deng, Wei Dong, Richard Socher, et al · 2009
Earlier work this paper cites.
Multiple incremental decremental learning of support vector machines
Masayuki Karasuyama and Ichiro Takeuchi. 2009 · 2009
Earlier work this paper cites.
Learning your identity and disease from research papers: information leaks in genome wide association study. In CCS . 534–544
Rui Wang, Yong Fuga Li, XiaoFeng Wang, Haixu Tang, and Xiaoyong Zhou. 2009 · 2009
Earlier work this paper cites.
Multiple incremental decremental learning of support vector machines
Masayuki Karasuyama and Ichiro Takeuchi. 2010 · 2010
Earlier work this paper cites.
Differentially private empirical risk minimization
Kamalika Chaudhuri, Claire Monteleoni, and Anand D Sarwate. 2011 · 2011
Earlier work this paper cites.
From extractable collision resistance to succinct non-interactive arguments of knowledge, and back again. In ITCS . 326–349
Nir Bitansky, Ran Canetti, Alessandro Chiesa, and Eran Tromer. 2012 · 2012
Earlier work this paper cites.
The EU Proposal for a General Data Protection Regulation and the roots of the ‘right to be forgotten’
Alessandro Mantelero. 2013 · 2013
Earlier work this paper cites.
The algorithmic foundations of differential privacy
Cynthia Dwork, Aaron Roth, et al · 2014
Earlier work this paper cites.
Privacy in pharmacogenetics: An { \{ End-to-End } \} case study of personalized warfarin dosing. In USENIX Security . 17–32
Matthew Fredrikson, Eric Lantz, Somesh Jha, Simon Lin, David Page, and Thomas Ristenpart. 2014 · 2014
Earlier work this paper cites.
Incremental and decremental training for linear classification. In KDD . 343–352
Cheng-Hao Tsai, Chieh-Yen Lin, and Chih-Jen Lin. 2014 · 2014
Earlier work this paper cites.
Total variation distance and the distribution of relative information. In ITA . 1–3
Sergio Verdú. 2014 · 2014
Earlier work this paper cites.
Towards making systems forget with machine unlearning. In 2015 IEEE Symposium on Security and Privacy . 463–480
Yinzhi Cao and Junfeng Yang. 2015 · 2015
Earlier work this paper cites.
Deep learning and the information bottleneck principle. In ITW . 1–5
Naftali Tishby and Noga Zaslavsky. 2015 · 2015
Earlier work this paper cites.
Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop
Original
Fisher Yu, Ari Seff, Yinda Zhang, Shuran Song, Thomas Funkhouser, and Jianxiong Xiao. 2015 · 2015
Earlier work this paper cites.
Deep learning with differential privacy. In SIGSAC . 308–318
Martin Abadi, Andy Chu, Ian Goodfellow, H Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang. 2016 · 2016
Earlier work this paper cites.
A multi-batch L-BFGS method for machine learning
Albert S Berahas, Jorge Nocedal, et al · 2016
Earlier work this paper cites.
Approximate data deletion from machine learning models. In AISTAT . 2008–2016
Zachary Izzo, Mary Anne Smart, Kamalika Chaudhuri, and James Zou. 2021 · 2016
Earlier work this paper cites.
Overcoming catastrophic forgetting in neural networks
James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, et al · 2017
Earlier work this paper cites.
Understanding black-box predictions via influence functions. In ICML . 1885–1894
Pang Wei Koh et al · 2017
Earlier work this paper cites.
Communication-efficient learning of deep networks from decentralized data. In AISTAT . 1273–1282
Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017 · 2017
Earlier work this paper cites.
Membership inference attacks against machine learning models. In SP . 3–18
Reza Shokri, Marco Stronati, Congzheng Song, and Vitaly Shmatikov. 2017 · 2017
Earlier work this paper cites.
Opening the black box of deep neural networks via information
Original
Ravid Shwartz-Ziv and Naftali Tishby. 2017 · 2017
Earlier work this paper cites.
Data leakage detection using cloud computing
Abhijeet Singh and Abhineet Anand. 2017 · 2017
Earlier work this paper cites.
Retaining Data from Streams of Social Platforms with Minimal Regret. In IJCAI . 2850–2856
Nguyen Thanh Tam, Matthias Weidlich, Duong Chi Thang, Hongzhi Yin, and Nguyen Quoc Viet Hung. 2017 · 2017
Earlier work this paper cites.
The eu general data protection regulation (gdpr)
Paul Voigt and Axel Von dem Bussche. 2017 · 2017
Earlier work this paper cites.
A progressive batching L-BFGS method for machine learning. In ICML . 620–629
Raghu Bollapragada, Jorge Nocedal, Dheevatsa Mudigere, Hao-Jun Shi, and Ping Tak Peter Tang. 2018 · 2018
Earlier work this paper cites.
Efficient repair of polluted machine learning systems via causal unlearning. In ASIACCS . 735–747
Yinzhi Cao, Alexander Fangxiao Yu, Andrew Aday, Eric Stahl, Jon Merwine, and Junfeng Yang. 2018 · 2018
Earlier work this paper cites.
Deep face recognition: A survey. In SIBGRAPI . 471–478
Iacopo Masi, Yue Wu, Tal Hassner, and Prem Natarajan. 2018 · 2018
Earlier work this paper cites.
The California consumer privacy act: Towards a European-style privacy regime in the United States
Stuart L Pardau. 2018 · 2018
Earlier work this paper cites.
Bayesian neural networks with weight sharing using Dirichlet processes
Wolfgang Roth and Franz Pernkopf. 2018 · 2018
Earlier work this paper cites.
Algorithms that remember: model inversion attacks and data protection law
Michael Veale, Reuben Binns, and Lilian Edwards. 2018 · 2018
Earlier work this paper cites.
Humans forget, machines remember: Artificial intelligence and the right to be forgotten
Eduard Fosch Villaronga, Peter Kieseberg, and Tiffany Li. 2018 · 2018
Earlier work this paper cites.
AI can be sexist and racist – it’s time to make it fair
James Zou and Londa Schiebinger. 2018 · 2018
Earlier work this paper cites.
A novel online incremental and decremental learning algorithm based on variable support vector machine
Yuantao Chen, Jie Xiong, Weihong Xu, and Jingwen Zuo. 2019 · 2019
Earlier work this paper cites.
Lifelong anomaly detection through unlearning. In SIGSAC . 1283–1297
Min Du, Zhi Chen, et al · 2019
Earlier work this paper cites.
Combining Neural Networks with Personalized PageRank for Classification on Graphs. In ICLR
Johannes Gasteiger, Aleksandar Bojchevski, and Stephan Günnemann. 2019 · 2019
Earlier work this paper cites.
Making ai forget you: Data deletion in machine learning
Antonio Ginart, Melody Guan, Gregory Valiant, and James Y Zou. 2019 · 2019
Earlier work this paper cites.
A geometric view of optimal transportation and generative model
Na Lei, Kehua Su, Li Cui, Shing-Tung Yau, and Xianfeng David Gu. 2019 · 2019
Earlier work this paper cites.
Zero-shot knowledge transfer via adversarial belief matching
Paul Micaelli et al · 2019
Earlier work this paper cites.
Debunking Misinformation on the Web: Detection, Validation, and Visualisation
Thanh Tam Nguyen. 2019 · 2019
Earlier work this paper cites.
Continual lifelong learning with neural networks: A review
German I Parisi, Ronald Kemker, Jose L Part, Christopher Kanan, and Stefan Wermter. 2019 · 2019
Earlier work this paper cites.
ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models. In NDSS
Ahmed Salem, Yang Zhang, Mathias Humbert, Pascal Berrang, Mario Fritz, and Michael Backes. 2019 · 2019
Earlier work this paper cites.
Making machine learning forget. In Annual Privacy Forum . 72–83
Saurabh Shintre et al · 2019
Earlier work this paper cites.
Neural cleanse: Identifying and mitigating backdoor attacks in neural networks. In SP . 707–723
Bolun Wang, Yuanshun Yao, Shawn Shan, Huiying Li, Bimal Viswanath, Haitao Zheng, and Ben Y Zhao. 2019 · 2019
Earlier work this paper cites.
Simplifying graph convolutional networks. In ICML . 6861–6871
Felix Wu, Amauri Souza, Tianyi Zhang, Christopher Fifty, Tao Yu, and Kilian Weinberger. 2019 · 2019
Earlier work this paper cites.
Machine unlearning: Linear filtration for logit-based classifiers
Original
Thomas Baumhauer, Pascal Schöttle, and Matthias Zeppelzauer. 2020 · 2020
Earlier work this paper cites.
Graph representation learning: a survey
Fenxiao Chen, Yun-Cheng Wang, Bin Wang, et al · 2020
Earlier work this paper cites.
Unlearning scanner bias for mri harmonisation. In MICCAI . 369–378
Nicola K Dinsdale, Mark Jenkinson, et al · 2020
Earlier work this paper cites.
On training deep neural networks using a streaming approach
Piotr Duda, Maciej Jaworski, Andrzej Cader, and Lipo Wang. 2020 · 2020
Earlier work this paper cites.
Class Clown: Data Redaction in Machine Unlearning at Enterprise Scale
Original
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 · 2020
Earlier work this paper cites.
Formalizing data deletion in the context of the right to be forgotten. In EUROCRYPT . 373–402
Sanjam Garg, Shafi Goldwasser, and Prashant Nalini Vasudevan. 2020 · 2020
Earlier work this paper cites.
A survey of learning causality with data: Problems and methods
Ruocheng Guo, Lu Cheng, Jundong Li, P Richard Hahn, and Huan Liu. 2020a · 2020
Earlier work this paper cites.
Graph representation learning
William L Hamilton. 2020 · 2020
Earlier work this paper cites.
Federated unlearning
Original
Gaoyang Liu, Xiaoqiang Ma, Yang Yang, Chen Wang, and Jiangchuan Liu. 2020b · 2020
Earlier work this paper cites.
Have you forgotten? A method to assess if machine learning models have forgotten data. In MICCAI . 95–105
Xiao Liu and Sotirios A Tsaftaris. 2020 · 2020
Earlier work this paper cites.
Learn to forget: Machine unlearning via neuron masking
Original
Yang Liu, Zhuo Ma, Ximeng Liu, Jian Liu, Zhongyuan Jiang, Jianfeng Ma, Philip Yu, and Kui Ren. 2020a · 2020
Earlier work this paper cites.
New insights and perspectives on the natural gradient method
James Martens. 2020 · 2020
Earlier work this paper cites.

Similar

Learning from failure: De-biasing classifier from biased classifier
Junhyun Nam, Hyuntak Cha, Sungsoo Ahn, Jaeho Lee, and Jinwoo Shin. 2020 · 2020
Cited alongside, same era.
Variational bayesian unlearning
Quoc Phong Nguyen, Bryan Kian Hsiang Low, and Patrick Jaillet. 2020 · 2020
Cited alongside, same era.
Uncertainty in neural networks: Approximately bayesian ensembling. In AISTATS . 234–244
Tim Pearce, Felix Leibfried, and Alexandra Brintrup. 2020 · 2020
Cited alongside, same era.
Adversarial attacks and defenses in deep learning
Kui Ren, Tianhang Zheng, Zhan Qin, and Xue Liu. 2020c · 2020
Cited alongside, same era.
{ \{ Updates-Leak } \} : Data Set Inference and Reconstruction Attacks in Online Learning. In USENIX Security . 1291–1308
Ahmed Salem, Apratim Bhattacharya, Michael Backes, Mario Fritz, and Yang Zhang. 2020 · 2020
Cited alongside, same era.
Learning mathematics “Asyik” with Youtube educative media. In Journal of Physics: Conference Series , Vol. 1477. 022012
WN Sari, BS Samosir, N Sahara, L Agustina, and Y Anita. 2020 · 2020
Cited alongside, same era.
“Amnesia” - A Selection of Machine Learning Models That Can Forget User Data Very Fast. In CIDR
Sebastian Schelter. 2020 · 2020
Cited alongside, same era.
Protecting Personal Privacy against Una uthorized Deep Learning Models. In USENIX Security . 1–16
S Shan, E Wenger, J Zhang, H Li, H Zheng, and BY Zhao. 2020 · 2020
Cited alongside, same era.
Towards probabilistic verification of machine unlearning
Original
David Marco Sommer, Liwei Song, Sameer Wagh, and Prateek Mittal. 2020 · 2020
Cited alongside, same era.
Boosting methods for multi-class imbalanced data classification: an experimental review
Jafar Tanha, Yousef Abdi, Negin Samadi, Nazila Razzaghi, and Mohammad Asadpour. 2020 · 2020
Cited alongside, same era.
Towards fairness in visual recognition: Effective strategies for bias mitigation. In CVPR . 8919–8928
Zeyu Wang, Klint Qinami, Ioannis Christos Karakozis, Kyle Genova, Prem Nair, Kenji Hata, and Olga Russakovsky. 2020 · 2020
Cited alongside, same era.
Analyzing information leakage of updates to natural language models. In SIGSAC . 363–375
Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople, Victor Rühle, Andrew Paverd, Olga Ohrimenko, et al · 2020
Cited alongside, same era.

Then

Deletion Inference, Reconstruction, and Compliance in Machine (Un) Learning
Ji Gao, Sanjam Garg, Mohammad Mahmoody, and Prashant Nalini Vasudevan. 2022a · 2022
Closest in time.
VeriFi: Towards Verifiable Federated Unlearning
Original
Xiangshan Gao, Xingjun Ma, Jingyi Wang, Youcheng Sun, Bo Li, Shouling Ji, Peng Cheng, and Jiming Chen. 2022b · 2022
Closest in time.
Evaluating Inexact Unlearning Requires Revisiting Forgetting
Original
Shashwat Goel, Ameya Prabhu, and Ponnurangam Kumaraguru. 2022 · 2022
Closest in time.
Efficient Attribute Unlearning: Towards Selective Removal of Input Attributes from Feature Representations
Original
Tao Guo, Song Guo, Jiewei Zhang, Wenchao Xu, and Junxiao Wang. 2022 · 2022
Closest in time.
Federated Unlearning: How to Efficiently Erase a Client in FL?
Original
Anisa Halimi, Swanand Kadhe, Ambrish Rawat, and Nathalie Baracaldo. 2022 · 2022
Closest in time.
Measuring Forgetting of Memorized Training Examples
Original
Matthew Jagielski, Om Thakkar, Florian Tramèr, Daphne Ippolito, Katherine Lee, Nicholas Carlini, Eric Wallace, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, et al · 2022
Closest in time.
Continual Learning and Private Unlearning
Original
Bo Liu, Qiang Liu, et al · 2022
Closest in time.
Forgetting fast in recommender systems
Original
Wenyan Liu, Juncheng Wan, Xiaoling Wang, Weinan Zhang, Dell Zhang, and Hang Li. 2022c · 2022
Closest in time.
Backdoor Defense with Machine Unlearning
Original
Yang Liu, Mingyuan Fan, Cen Chen, Ximeng Liu, Zhuo Ma, Li Wang, and Jianfeng Ma. 2022a · 2022
Closest in time.
Quark: Controllable text generation with reinforced unlearning
Ximing Lu, Sean Welleck, Jack Hessel, Liwei Jiang, Lianhui Qin, Peter West, Prithviraj Ammanabrolu, and Yejin Choi. 2022 · 2022
Closest in time.
Certifiable Unlearning Pipelines for Logistic Regression: An Experimental Study
Ananth Mahadevan and Michael Mathioudakis. 2022 · 2022
Closest in time.
Hard to Forget: Poisoning Attacks on Certified Machine Unlearning. In AAAI , Vol. 36. 7691–7700
Neil G Marchant, Benjamin IP Rubinstein, and Scott Alfeld. 2022 · 2022
Closest in time.
Deep Unlearning via Randomized Conditionally Independent Hessians. In CVPR . 10422–10431
Ronak Mehta, Sourav Pal, Vikas Singh, and Sathya N Ravi. 2022 · 2022
Closest in time.
An Introduction to Machine Unlearning
Original
Salvatore Mercuri, Raad Khraishi, Ramin Okhrati, Devesh Batra, Conor Hamill, Taha Ghasempour, and Andrew Nowlan. 2022a · 2022
Closest in time.
An introduction to machine unlearning
Original
Salvatore Mercuri, Raad Khraishi, Ramin Okhrati, Devesh Batra, Conor Hamill, Taha Ghasempour, and Andrew Nowlan. 2022b · 2022
Closest in time.
A Survey of Machine Unlearning
Original
Thanh Tam Nguyen, Thanh Trung Huynh, Phi Le Nguyen, Alan Wee-Chung Liew, Hongzhi Yin, and Quoc Viet Hung Nguyen. 2022a · 2022
Closest in time.
Prototype learning for interpretable respiratory sound analysis. In ICASSP . 9087–9091
Zhao Ren, Thanh Tam Nguyen, and Wolfgang Nejdl. 2022 · 2022
Closest in time.
Anatomizing bias in facial analysis. In AAAI , Vol. 36. 12351–12358
Richa Singh, Puspita Majumdar, Surbhi Mittal, and Mayank Vatsa. 2022 · 2022
Closest in time.
Athena: Probabilistic Verification of Machine Unlearning
David Marco Sommer, Liwei Song, Sameer Wagh, and Prateek Mittal. 2022 · 2022
Closest in time.
Bounding Membership Inference
Original
Anvith Thudi, Ilia Shumailov, Franziska Boenisch, and Nicolas Papernot. 2022c · 2022
Closest in time.
Efficiently Maintaining Next Basket Recommendations under Additions and Deletions of Baskets and Items
Original
Benjamin Longxiang Wang and Sebastian Schelter. 2022 · 2022
Closest in time.
Federated unlearning via class-discriminative pruning. In WWW . 622–632
Junxiao Wang, Song Guo, et al · 2022
Closest in time.
Federated unlearning with knowledge distillation
Original
Chen Wu, Sencun Zhu, and Prasenjit Mitra. 2022c · 2022
Closest in time.
Federated Unlearning: Guarantee the Right of Clients to Forget
Leijie Wu, Song Guo, Junxiao Wang, Zicong Hong, Jie Zhang, and Yaohong Ding. 2022a · 2022
Closest in time.
Few-Shot Unlearning by Model Inversion
Original
Youngsik Yoon, Jinhwan Nam, Hyojeong Yun, Dongwoo Kim, and Jungseul Ok. 2022 · 2022
Closest in time.
Machine Unlearning for Image Retrieval: A Generative Scrubbing Approach. In MM . 237–245
Peng-Fei Zhang, Guangdong Bai, Zi Huang, and Xin-Shun Xu. 2022 · 2022
Closest in time.
Unlearn What You Want to Forget: Efficient Unlearning for LLMs. In EMNLP , Houda Bouamor, Juan Pino, and Kalika Bali (Eds.). 12041–12052
Jiaao Chen and Diyi Yang. 2023 · 2023
Closest in time.
GNNDelete: A General Strategy for Unlearning in Graph Neural Networks. In ICLR
Jiali Cheng, George Dasoulas, Huan He, Chirag Agarwal, and Marinka Zitnik. 2023 · 2023
Closest in time.
Efficiently forgetting what you have learned in graph representation learning via projection. In AISTATS . 6674–6703
Weilin Cong and Mehrdad Mahdavi. 2023 · 2023
Closest in time.
Safe: Machine unlearning with shard graphs. In ICCV . 17108–17118
Yonatan Dukler, Benjamin Bowman, Alessandro Achille, Aditya Golatkar, Ashwin Swaminathan, and Stefano Soatto. 2023 · 2023
Closest in time.
A Decision-Making Process to Implement the ‘Right to Be Forgotten’in Machine Learning. In Annual Privacy Forum . 20–38
Katie Hawkins, Nora Alhuwaish, Sana Belguith, Asma Vranaki, and Andrew Charlesworth. 2023 · 2023
Closest in time.
FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs. In SoLaR
Swanand Kadhe, Anisa Halimi, Ambrish Rawat, and Nathalie Baracaldo. 2023 · 2023
Closest in time.
Preserving privacy through dememorization: An unlearning technique for mitigating memorization risks in language models. In EMNLP . 4360–4379
Aly Kassem, Omar Mahmoud, and Sherif Saad. 2023 · 2023
Closest in time.
Making users indistinguishable: Attribute-wise unlearning in recommender systems. In MM . 984–994
Yuyuan Li, Chaochao Chen, Xiaolin Zheng, Yizhao Zhang, Zhongxuan Han, Dan Meng, and Jun Wang. 2023 · 2023
Closest in time.
Erm-ktp: Knowledge-level machine unlearning via knowledge transfer. In CVPR . 20147–20155
Shen Lin, Xiaoyu Zhang, Chenyang Chen, Xiaofeng Chen, and Willy Susilo. 2023 · 2023
Closest in time.
A survey on federated unlearning: Challenges, methods, and future directions
Ziyao Liu, Yu Jiang, Jiyuan Shen, Minyi Peng, Kwok-Yan Lam, Xingliang Yuan, and Xiaoning Liu. 2023 · 2023
Closest in time.
Unlearning graph classifiers with limited data resources. In WWW . 716–726
Chao Pan, Eli Chien, and Olgica Milenkovic. 2023 · 2023
Closest in time.
FAST: Feature Aware Similarity Thresholding for Weak Unlearning in Black-Box Generative Models
Original
Subhodip Panda and Prathosh AP. 2023 · 2023
Closest in time.
FedCIO: Efficient Exact Federated Unlearning with Clustering, Isolation, and One-shot Aggregation. In BigData . 5559–5568
Hongyu Qiu, Yongwei Wang, Yonghui Xu, Lizhen Cui, and Zhiqi Shen. 2023 · 2023
Closest in time.
Exploring the landscape of machine unlearning: A comprehensive survey and taxonomy
Original
Thanveer Shaik, Xiaohui Tao, Haoran Xie, Lin Li, Xiaofeng Zhu, and Qing Li. 2023 · 2023
Closest in time.
Adapt then unlearn: Exploiting parameter space semantics for unlearning in generative adversarial networks
Original
Piyush Tiwary, Atri Guha, Subhodip Panda, et al · 2023
Closest in time.
Deltaboost: Gradient boosting decision trees with efficient machine unlearning
Zhaomin Wu, Junhui Zhu, Qinbin Li, and Bingsheng He. 2023 · 2023
Closest in time.
Machine Unlearning: A Survey
Heng Xu, Tianqing Zhu, Lefeng Zhang, Wanlei Zhou, and Philip S. Yu. 2023 · 2023
Closest in time.
One-Shot Machine Unlearning with Mnemonic Code
Original
Tomoya Yamashita, Masanori Yamada, and Takashi Shibata. 2023 · 2023
Closest in time.
Federated unlearning for on-device recommendation. In WSDM . 393–401
Wei Yuan, Hongzhi Yin, Fangzhao Wu, Shijie Zhang, Tieke He, and Hao Wang. 2023 · 2023
Closest in time.
Machine unlearning methodology based on stochastic teacher network. In ADMA . 250–261
Xulong Zhang, Jianzong Wang, Ning Cheng, Yifu Sun, Chuanyao Zhang, and Jing Xiao. 2023 · 2023
Closest in time.
Heterogeneous federated knowledge graph embedding learning and unlearning. In WWW . 2444–2454
Xiangrong Zhu, Guangyao Li, and Wei Hu. 2023 · 2023
Closest in time.
Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Images
Original
Jacopo Bonato, Marco Cotogni, and Luigi Sabetta. 2024 · 2024
Closest in time.
SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization. In AISTATS . 3457–3465
Yann Fraboni, Martin Van Waerebeke, Kevin Scaman, Richard Vidal, Laetitia Kameni, and Marco Lorenzi. 2024 · 2024
Closest in time.
Separate the wheat from the chaff: Model deficiency unlearning via parameter-efficient module operation. In AAAI , Vol. 38. 18252–18260
Xinshuo Hu, Dongfang Li, Baotian Hu, Zihao Zheng, Zhenyu Liu, and Min Zhang. 2024 · 2024
Closest in time.
Fast-fedul: A training-free federated unlearning with provable skew resilience. In ECML-PKDD . 55–72
Thanh Trung Huynh, Trong Bang Nguyen, Phi Le Nguyen, Thanh Tam Nguyen, Matthias Weidlich, Quoc Viet Hung Nguyen, and Karl Aberer. 2024 · 2024
Closest in time.
Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer Level Attack and Knowledge Distillation. In AAAI , Vol. 38. 21241–21248
Hyunjune Kim, Sangyong Lee, and Simon S Woo. 2024 · 2024
Closest in time.
Learning and Unlearning to Operate Profitable Secure Electric Vehicle Charging
Sangyoon Lee and Dae-Hyun Choi. 2024 · 2024
Closest in time.
SFGCN: Synergetic Fusion-based Graph Convolutional Networks Approach for Link Prediction in Social Networks
Sang-Woong Lee, Jawad Tanveer, Amir Masoud Rahmani, Hamid Alinejad-Rokny, Parisa Khoshvaght, Gholamreza Zare, Pegah Malekpour Alamdari, and Mehdi Hosseinzadeh. 2024 · 2024
Closest in time.
Dissecting Language Models: Machine Unlearning via Selective Pruning
Original
Nicholas Pochinkov and Nandi Schoots. 2024 · 2024
Closest in time.
Framu: Attention-based machine unlearning using federated reinforcement learning
Thanveer Shaik, Xiaohui Tao, Lin Li, Haoran Xie, Taotao Cai, Xiaofeng Zhu, and Qing Li. 2024 · 2024
Closest in time.
Federated Unlearning: a Perspective of Stability and Fairness
Original
Jiaqi Shao, Tao Lin, Xuanyu Cao, and Bing Luo. 2024 · 2024
Closest in time.
Multi-Modal Recommendation Unlearning
Original
Yash Sinha, Murari Mandal, and Mohan Kankanhalli. 2024 · 2024
Closest in time.
Communication Efficient and Provable Federated Unlearning
Youming Tao, Cheng-Long Wang, Miao Pan, Dongxiao Yu, Xiuzhen Cheng, and Di Wang. 2024 · 2024
Closest in time.
Towards Efficient and Effective Unlearning of Large Language Models for Recommendation
Original
Hangyu Wang, Jianghao Lin, Bo Chen, Yang Yang, Ruiming Tang, Weinan Zhang, and Yong Yu. 2024b · 2024
Closest in time.
Unlearning with Control: Assessing Real-world Utility for Large Language Model Unlearning
Original
Qizhou Wang, Bo Han, Puning Yang, Jianing Zhu, Tongliang Liu, and Masashi Sugiyama. 2024a · 2024
Closest in time.
Machine unlearning: Solutions and challenges
Jie Xu, Zihan Wu, Cong Wang, and Xiaohua Jia. 2024 · 2024
Closest in time.
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
Original
Yimeng Zhang, Xin Chen, Jinghan Jia, Yihua Zhang, Chongyu Fan, Jiancheng Liu, Mingyi Hong, Ke Ding, and Sijia Liu. 2024a · 2024
Closest in time.
Unlearncanvas: A stylized image dataset to benchmark machine unlearning for diffusion models
Original
Yihua Zhang, Yimeng Zhang, Yuguang Yao, Jinghan Jia, Jiancheng Liu, Xiaoming Liu, and Sijia Liu. 2024b · 2024
Closest in time.
Decoupling the Class Label and the Target Concept in Machine Unlearning
Original
Jianing Zhu, Bo Han, Jiangchao Yao, Jianliang Xu, Gang Niu, and Masashi Sugiyama. 2024 · 2024
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…