Continual Learning and Private Unlearning

As intelligent agents become autonomous over longer periods of time, they may eventually become lifelong counterparts to specific people. If so, it may be common for a user to want the agent to master a task temporarily but later on to forget the task due to privacy concerns. However enabling an agent to \emph{forget privately} what the user specified without degrading the rest of the learned knowledge is a challenging problem. With the aim of addressing this challenge, this paper formalizes this continual learning and private unlearning (CLPU) problem. The paper further introduces a straightforward but exactly private solution, CLPU-DER++, as the first step towards solving the CLPU problem, along with a set of carefully designed benchmark problems to evaluate the effectiveness of the proposed solution. The code is available at https://github.com/Cranial-XIX/Continual-Learning-Private-Unlearning.

[1]  Takashi Shibata,et al.  Learning with Selective Forgetting , 2021, IJCAI.

[2]  Bo Liu,et al.  A Lifelong Learning Approach to Mobile Robot Navigation , 2021, IEEE Robotics and Automation Letters.

[3]  Bo Liu,et al.  Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks , 2021, NeurIPS.

[4]  Stefano Soatto,et al.  Mixed-Privacy Forgetting in Deep Networks , 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Magdalena Biesialska,et al.  Continual Lifelong Learning in Natural Language Processing: A Survey , 2020, COLING.

[6]  Daniel Lowd,et al.  Machine Unlearning for Random Forests , 2020, ICML.

[7]  Yinjun Wu,et al.  DeltaGrad: Rapid retraining of machine learning models , 2020, ICML.

[8]  Simone Calderara,et al.  Dark Experience for General Continual Learning: a Strong, Simple Baseline , 2020, NeurIPS.

[9]  Stefano Soatto,et al.  Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  L. V. D. Maaten,et al.  Certified Data Removal from Machine Learning Models , 2019, ICML.

[11]  Yi-Ming Chan,et al.  Compacting, Picking and Growing for Unforgetting Continual Learning , 2019, NeurIPS.

[12]  Tinne Tuytelaars,et al.  A Continual Learning Survey: Defying Forgetting in Classification Tasks , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Kristina Lerman,et al.  A Survey on Bias and Fairness in Machine Learning , 2019, ACM Comput. Surv..

[14]  James Zou,et al.  Making AI Forget You: Data Deletion in Machine Learning , 2019, NeurIPS.

[15]  Yi-Ming Chan,et al.  Increasingly Packing Multiple Facial-Informatics Modules in A Unified Deep-Learning Model via Lifelong Learning , 2019, ICMR.

[16]  E. Bjork,et al.  Forgetting as the friend of learning: implications for teaching and self-regulated learning. , 2019, Advances in physiology education.

[17]  Andreas S. Tolias,et al.  Three scenarios for continual learning , 2019, ArXiv.

[18]  Marc'Aurelio Ranzato,et al.  On Tiny Episodic Memories in Continual Learning , 2019 .

[19]  Tinne Tuytelaars,et al.  Task-Free Continual Learning , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Marc'Aurelio Ranzato,et al.  Efficient Lifelong Learning with A-GEM , 2018, ICLR.

[21]  G. Tesauro,et al.  Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference , 2018, ICLR.

[22]  Sungroh Yoon,et al.  Security and Privacy Issues in Deep Learning , 2018, ArXiv.

[23]  Yee Whye Teh,et al.  Progress & Compress: A scalable framework for continual learning , 2018, ICML.

[24]  Philip H. S. Torr,et al.  Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence , 2018, ECCV.

[25]  Svetlana Lazebnik,et al.  Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights , 2018, ECCV.

[26]  Svetlana Lazebnik,et al.  PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[27]  Sung Ju Hwang,et al.  Lifelong Learning with Dynamically Expandable Networks , 2017, ICLR.

[28]  Marc'Aurelio Ranzato,et al.  Gradient Episodic Memory for Continual Learning , 2017, NIPS.

[29]  John K. Tsotsos,et al.  Incremental Learning Through Deep Adaptation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Jiwon Kim,et al.  Continual Learning with Deep Generative Replay , 2017, NIPS.

[31]  Andrei A. Rusu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[32]  Derek Hoiem,et al.  Learning without Forgetting , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[33]  Razvan Pascanu,et al.  Progressive Neural Networks , 2016, ArXiv.

[34]  Junfeng Yang,et al.  Towards Making Systems Forget with Machine Unlearning , 2015, 2015 IEEE Symposium on Security and Privacy.

[35]  Chris W. Johnson.  Unlearning , 2005, BMJ : British Medical Journal.

[36]  R. French.  Catastrophic forgetting in connectionist networks , 1999, Trends in Cognitive Sciences.

[37]  Anthony V. Robins,et al.  Catastrophic Forgetting, Rehearsal and Pseudorehearsal , 1995, Connect. Sci..