2023

Towards Unbounded Machine Unlearning

Kurmanji, Meghdad, Triantafillou, Peter, Hayes, Jamie et al.

Understand

Deep machine unlearning is the problem of `removing' from a trained neural network a subset of its training set.

This problem is very timely and has many applications, including the key tasks of removing biases (RB), resolving confusion (RC) (caused by mislabelled data in trained models), as well as allowing users to exercise their `right to be forgotten' to protect User Privacy (UP).
This paper is the first, to our knowledge, to study unlearning for different applications (RB, RC, UP), with the view that each has its own desiderata, definitions for `forgetting' and associated metrics for forget quality.
For UP, we propose a novel adaptation of a strong Membership Inference Attack for unlearning.

Built on

Learning multiple layers of features from tiny images
Alex Krizhevsky, Geoffrey Hinton, et al · 2009
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
Earlier work this paper cites.
The algorithmic foundations of differential privacy
Cynthia Dwork, Aaron Roth, et al · 2014
Earlier work this paper cites.
Generative adversarial nets
Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio · 2014
Earlier work this paper cites.
Striving for simplicity: The all convolutional net
Original
Jost Tobias Springenberg, Alexey Dosovitskiy, Thomas Brox, and Martin Riedmiller · 2014
Earlier work this paper cites.
Towards making systems forget with machine unlearning
Yinzhi Cao and Junfeng Yang · 2015
Earlier work this paper cites.
Distilling the knowledge in a neural network
Original
Geoffrey Hinton, Oriol Vinyals, Jeff Dean, et al · 2015
Earlier work this paper cites.
Deep learning with differential privacy
Martin Abadi, Andy Chu, Ian Goodfellow, H Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang · 2016
Earlier work this paper cites.
Deep residual learning for image recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun · 2016
Earlier work this paper cites.
A closer look at memorization in deep networks
Devansh Arpit, Stanisław Jastrzębski, Nicolas Ballas, David Krueger, Emmanuel Bengio, Maxinder S Kanwal, Tegan Maharaj, Asja Fischer, Aaron Courville, Yoshua Bengio, et al · 2017
Earlier work this paper cites.
Membership inference attacks against machine learning models
Reza Shokri, Marco Stronati, Congzheng Song, and Vitaly Shmatikov · 2017
Earlier work this paper cites.
Neural tangent kernel: Convergence and generalization in neural networks
Arthur Jacot, Franck Gabriel, and Clément Hongler · 2018
Earlier work this paper cites.
Manipulating machine learning: Poisoning attacks and countermeasures for regression learning
Matthew Jagielski, Alina Oprea, Battista Biggio, Chang Liu, Cristina Nita-Rotaru, and Bo Li · 2018
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
Earlier work this paper cites.

Similar

Certified data removal from machine learning models
Original
Chuan Guo, Tom Goldstein, Awni Hannun, and Laurens Van Der Maaten · 2019
Cited alongside, same era.
Continual lifelong learning with neural networks: A review
German I Parisi, Ronald Kemker, Jose L Part, Christopher Kanan, and Stefan Wermter · 2019
Cited alongside, same era.
A simple framework for contrastive learning of visual representations
Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton · 2020
Cited alongside, same era.
Bootstrap your own latent-a new approach to self-supervised learning
Jean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhaohan Guo, Mohammad Gheshlaghi Azar, et al · 2020
Cited alongside, same era.
Momentum contrast for unsupervised visual representation learning
Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick · 2020
Cited alongside, same era.
Self-training with noisy student improves ImageNet classification
Qizhe Xie, Minh-Thang Luong, Eduard Hovy, and Quoc V Le · 2020
Cited alongside, same era.
On hyperparameter optimization of machine learning algorithms: Theory and practice
Li Yang and Abdallah Shami · 2020
Cited alongside, same era.
The secret revealer: Generative model-inversion attacks against deep neural networks
Yuheng Zhang, Ruoxi Jia, Hengzhi Pei, Wenxiao Wang, Bo Li, and Dawn Song · 2020
Cited alongside, same era.
Machine unlearning
Lucas Bourtoule, Varun Chandrasekaran, Christopher A Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, and Nicolas Papernot · 2021
Cited alongside, same era.
When machine unlearning jeopardizes privacy
Min Chen, Zhikun Zhang, Tianhao Wang, Michael Backes, Mathias Humbert, and Yang Zhang · 2021
Cited alongside, same era.
Exploring simple siamese representation learning
Xinlei Chen and Kaiming He · 2021
Cited alongside, same era.
Mixed-privacy forgetting in deep networks
Aditya Golatkar, Alessandro Achille, Avinash Ravichandran, Marzia Polito, and Stefano Soatto · 2021
Cited alongside, same era.

Then

Descent-to-delete: Gradient-based methods for machine unlearning
Seth Neel, Aaron Roth, and Saeed Sharifi-Malvajerdi · 2021
Later among the works it cites.
Pervasive label errors in test sets destabilize machine learning benchmarks
Original
Curtis G Northcutt, Anish Athalye, and Jonas Mueller · 2021
Later among the works it cites.
Remember what you want to forget: Algorithms for machine unlearning
Ayush Sekhari, Jayadev Acharya, Gautam Kamath, and Ananda Theertha Suresh · 2021
Later among the works it cites.
Understanding deep learning (still) requires rethinking generalization
Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals · 2021
Later among the works it cites.
Membership inference attacks from first principles
Nicholas Carlini, Steve Chien, Milad Nasr, Shuang Song, Andreas Terzis, and Florian Tramer · 2022
Later among the works it cites.
Can bad teaching induce forgetting? unlearning in deep networks using an incompetent teacher
Original
Vikram S Chundawat, Ayush K Tarun, Murari Mandal, and Mohan Kankanhalli · 2022
Later among the works it cites.
A survey on bias in visual datasets
Simone Fabbrizzi, Symeon Papadopoulos, Eirini Ntoutsi, and Ioannis Kompatsiaris · 2022
Later among the works it cites.
Evaluating inexact unlearning requires revisiting forgetting
Original
Shashwat Goel, Ameya Prabhu, and Ponnurangam Kumaraguru · 2022
Later among the works it cites.
Efficient two-stage model retraining for machine unlearning
Junyaup Kim and Simon S Woo · 2022
Later among the works it cites.
Unrolling sgd: Understanding factors influencing machine unlearning
Anvith Thudi, Gabriel Deza, Varun Chandrasekaran, and Nicolas Papernot · 2022
Later among the works it cites.
Federated unlearning with knowledge distillation
Original
Chen Wu, Sencun Zhu, and Prasenjit Mitra · 2022
Later among the works it cites.
Prompt certified machine unlearning with randomized gradient smoothing and quantization
Zijie Zhang, Yang Zhou, Xin Zhao, Tianshi Che, and Lingjuan Lyu · 2022
Later among the works it cites.
Tight bounds for machine unlearning via differential privacy
Original
Yiyang Huang and Clément L Canonne · 2023
Closest in time.
Neurips 2023 - machine unlearning, 2023
Eleni Triantafillou, Fabian Pedregosa, Jamie Hayes, Peter Kairouz, Isabelle Guyon, Meghdad Kurmanji, Gintare Karolina Dziugaite, Peter Triantafillou, Kairan Zhao, Lisheng Sun Hosoya, Julio C. S. Jacques Junior, Vincent Dumoulin, Ioannis Mitliagkas, Sergio Escalera, Jun Wan, Sohier Dane, Maggie Demkin, and Walter Reade · 2023
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…