adversarial continual learning
play

Adversarial Continual Learning Sayna Ebrahimi Franziska Meier - PowerPoint PPT Presentation

Sep 24, 2022 •232 likes •592 views

Adversarial Continual Learning Sayna Ebrahimi Franziska Meier Roberto Calandra Trevor Darrell Marcus Rohrbach UC Berkeley Facebook AI Research Facebook AI Research UC Berkeley Facebook AI Research What is Continual Learning? Definition:

  1. Adversarial Continual Learning Sayna Ebrahimi Franziska Meier Roberto Calandra Trevor Darrell Marcus Rohrbach UC Berkeley Facebook AI Research Facebook AI Research UC Berkeley Facebook AI Research

  2. What is Continual Learning? Definition: learning a sequence of tasks and performing well on all of them Objectives: Task 3 Task 2 Task 1 • No forgetting • Data streams and revisiting is not allowed/limited • High knowledge transferability • Efficiency and scalability • No/limited task information at test time • etc.

  3. Approaches in Continual Learning LWF: Li & Hoiem, 2016 LWF: Li & Hoiem, 2016 LFL: Jung et al., 2016 LFL: Jung et al., 2016 EWC: Kirkpatrick et al., 2016 SI EWC EWC: Kirkpatrick et al., 2016 SI: Zenke et al., 2017 MAS SI: Zenke et al., 2017 VCL: Nguyen et al., 2017 MAS: Aljundi, 2018 MAS: Aljundi, 2018 Regularization UCB: Ebrahimi et al., 2020 UCB: Ebrahimi et al., 2020 LFL LWF UCB VCL

  4. Approaches in Continual Learning LWF: Li & Hoiem, 2016 LWF: Li & Hoiem, 2016 LFL: Jung et al., 2016 LFL: Jung et al., 2016 EWC: Kirkpatrick et al., 2016 SI EWC EWC: Kirkpatrick et al., 2016 SI: Zenke et al., 2017 MAS SI: Zenke et al., 2017 VCL: Nguyen et al., 2017 MAS: Aljundi, 2018 MAS: Aljundi, 2018 Regularization UCB: Ebrahimi et al., 2020 UCB: Ebrahimi et al., 2020 LFL LWF UCB VCL A-GEM GEM Memory Experience replay : Robins, 1995 GEM: Lopez-Paz & Ranzato, 2017 Experience replay A-GEM: Chaudhry et al., 2019

  5. Approaches in Continual Learning LWF: Li & Hoiem, 2016 LWF: Li & Hoiem, 2016 LFL: Jung et al., 2016 LFL: Jung et al., 2016 EWC: Kirkpatrick et al., 2016 SI EWC EWC: Kirkpatrick et al., 2016 SI: Zenke et al., 2017 MAS SI: Zenke et al., 2017 VCL: Nguyen et al., 2017 MAS: Aljundi, 2018 MAS: Aljundi, 2018 Regularization UCB: Ebrahimi et al., 2020 UCB: Ebrahimi et al., 2020 LFL LWF UCB VCL A-GEM PNN GEM Structure Memory Experience replay : Robins, 1995 PC GEM: Lopez-Paz & Ranzato, 2017 DEN Experience replay PNN : Rusu et al., 2016 A-GEM: Chaudhry et al., 2019 DEN : Yoon et al., 2018 PC: Schwarz et al., 2018

  6. Approaches in Continual Learning LWF: Li & Hoiem, 2016 LWF: Li & Hoiem, 2016 LFL: Jung et al., 2016 LFL: Jung et al., 2016 EWC: Kirkpatrick et al., 2016 SI EWC EWC: Kirkpatrick et al., 2016 SI: Zenke et al., 2017 MAS SI: Zenke et al., 2017 VCL: Nguyen et al., 2017 MAS: Aljundi, 2018 MAS: Aljundi, 2018 Regularization UCB: Ebrahimi et al., 2020 UCB: Ebrahimi et al., 2020 LFL LWF UCB iCaRL: Rebuffi et al., 2016 VCL PackNet iCaRL Piggyback PackNet: Mallya, 2018 A-GEM Piggyback: Mallya 2018 PNN HAT HAT: Serrà et al., 2018 GEM DGR Structure Memory FearNet Experience replay : Robins, 1995 PC GEM: Lopez-Paz & Ranzato, 2017 DEN Experience replay PNN : Rusu et al., 2016 A-GEM: Chaudhry et al., 2019 DEN : Yoon et al., 2018 PC: Schwarz et al., 2018 DGR: Shin et al ., 2017 FearNet: Kemker et al., 2017

  7. Where does our approach (ACL) stand? Memory Structure ACL

  8. Intuition • Tasks in a sequence • Have task-invariant (shared) knowledge in common • Require task-specific (private) features to master them Private (Task 1) Shared Knowledge Private (Task 2) (task-invariant) Private (Task 3) How can we factorize task-invariant from task-specific features?

  9. Our Approach: Adversarial Continual Learning Private (Task 1) Private Target label (Task 1) Private Private (Task 2) (Task 2) z P Private (Task 3) Private (Task 3) z S Shared Discriminator Task label Input images & task labels

  10. Our Approach: Adversarial Continual Learning Private (Task 1) Private Target label (Task 1) Private Private (Task 2) (Task 2) z P Private (Task 3) Private (Task 3) z S Shared Discriminator Task label Input images & task labels

  11. Our Approach: Adversarial Continual Learning Private (Task 1) Private Target label (Task 1) Private Private (Task 2) (Task 2) z P Private (Task 3) Private (Task 3) z S Shared Shared Discriminator Task label (task-invariant) Input images & task labels ℒ adv

  12. Our Approach: Adversarial Continual Learning Private (Task 1) Private Target label (Task 1) Private Private (Task 2) (Task 2) z P Private (Task 3) Private (Task 3) z S Shared Shared Discriminator Task label (task-invariant) Input images & task labels ℒ adv

  13. Our Approach: Adversarial Continual Learning Private (Task 1) Private Target label (Task 1) Private Private Target label (Task 2) (Task 2) z P Private (Task 3) Private (Task 3) ℒ di ff z S Shared Shared Shared Discriminator Task label (task-invariant) (task-invariant) Input images & task labels ℒ adv

  14. Our Approach: Adversarial Continual Learning Private (Task 1) Private Target label (Task 1) Private Private Target label (Task 2) (Task 2) z P Private Target label (Task 3) Private (Task 3) ℒ di ff z S Shared Discriminator Task label (task-invariant) Input images & task labels (x,t) ℒ adv

  15. Avoiding Forgetting in ACL Stored per task Private (Task 1) Private (Task 1) Private Private Target label (Task 2) (Task 2) z P Private (Task 3) Private (Task 3) ℒ di ff Experience z S Replay Shared Discriminator Task label (task-independent) Input images & task labels ℒ adv

  16. Experiments miniImageNet (20 Tasks) Average Accuracy CIFAR100 (20 Tasks) n ACC = 1 ∑ R i , n Split MNIST (5 Tasks) n i =1 Permuted MNIST (10/20/30/40 Tasks) Backward Transfer: Sequence of 5 datasets: n 1 ∑ BWT = R i , n − R i , i (SVHN, CIFAR10, MNIST, FashionMNIST, NotMNIST) n − 1 i =1 Evaluation metrics Datasets

  17. Results on 20-Split MiniImageNet ACC (%) ACL (Ours) 62.07 62.07 HAT 59.45 PNN 58.96 ER-RES 57.32 A-GEM 52.43 Ordinary Finetune 28.76 Accuracy (%) 0 63 70

  18. Results on 20-Split MiniImageNet ACL (Ours) 62.07 62.07 0.00 HAT 59.45 -0.04 PNN 0.00 58.96 ER-RES 57.32 -11.34 A-GEM 52.43 -15.23 Ordinary Finetune 28.76 -64.23 -70 0 70 63

  19. Results on 20-Split MiniImageNet ACL (Ours) 62.07 62.07 0.00 HAT 59.45 -0.04 PNN 58.96 0.00 ER-RES 57.32 -11.34 A-GEM 52.43 -15.23 Ordinary Finetune 28.76 -64.23 -70 0 70 63 Architecture Memory (MB) Replay Buffer (MB) ACL (Ours) 113.1 8.50 HAT 123.6 PNN 588.0 ER-RES 110.10 57.3 A-GEM 110.10 52.4 Ordinary Finetune 28.8 Memory (MB) 0 200 400 600

  20. Results on Sequence of 5-Datasets (SVHN, CIFAR10, MNIST, FashionMNIST, NotMNIST) # Classes Training Test 50 212,785 48,365

  21. Results on Sequence of 5-Datasets ACC (%) ACL (Ours) 78.55 78.55 UCB 76.34 Finetune 27.32 Accuracy (%) 0 80 (SVHN, CIFAR10, MNIST, FashionMNIST, NotMNIST) # Classes Training Test 79 50 212,785 48,365

  22. Results on Sequence of 5-Datasets ACL (Ours) 78.55 78.55 -0.01 UCB 76.34 -1.34 Ordinary Finetune -42.12 27.32 -80 0 80 Architecture Memory (MB) ACL (Ours) 16.5 UCB 32.8 79 Finetune 16.5 0 13.333 26.667 40

  23. Ablation Study on 20-Split miniImageNet ACC (%) BWT (%) Discriminator ℒ di ff Replay buffer X X X 62.07 0.00

  24. Ablation Study on 20-Split miniImageNet ACC (%) BWT (%) Discriminator ℒ di ff Replay buffer - X X 52.07 -0.01 X X X 62.07 0.00

  25. Ablation Study on 20-Split miniImageNet ACC (%) BWT (%) Discriminator ℒ di ff Replay buffer - X X 52.07 -0.01 X - X 57.66 -3.71 X X X 62.07 0.00

  26. Ablation Study on 20-Split miniImageNet ACC (%) BWT (%) Discriminator ℒ di ff Replay buffer X X 52.07 -0.01 X X 57.66 -3.71 X X - 60.28 0.00 X X X 62.07 0.00

  27. Visualizing Adversarial Learning Effect (20-Split miniImageNet) w. Discriminator w/o Discriminator Task Shared Private Shared Private Number Task 20 C1 C1 C1 C1 Without C2 C2 C2 C2 Dis C3 C3 C3 C3 C4 C4 C4 C4 C5 C5 C5 C5 T1 T1 T2 T2 T3 T3 T4 T4 T5 T5 Tasks 1-10 T6 T6 T7 T7 T8 T8 T9 T9 T10 T10

  28. Visualizing Adversarial Learning Effect (20-Split miniImageNet) w. Discriminator w/o Discriminator Task Shared Private Shared Private Number Task 20 C1 C1 C1 C1 Without C2 C2 C2 C2 Dis C3 C3 C3 C3 C4 C4 C4 C4 C5 C5 C5 C5 T1 T1 T2 T2 T3 T3 T4 T4 T5 T5 Tasks 1-10 T6 T6 T7 T7 T8 T8 T9 T9 T10 T10

  29. Visualizing Adversarial Learning Effect (20-Split miniImageNet) w. Discriminator w/o Discriminator Task Shared Private Shared Private Number Task 20 C1 C1 C1 C1 Without C2 C2 C2 C2 Dis C3 C3 C3 C3 C4 C4 C4 C4 C5 C5 C5 C5 T1 T1 T2 T2 T3 T3 T4 T4 T5 T5 Tasks 1-10 T6 T6 T7 T7 T8 T8 T9 T9 T10 T10

  30. Visualizing Adversarial Learning Effect (20-Split miniImageNet) w. Discriminator w/o Discriminator Task Shared Private Shared Private Number Task 20 C1 C1 C1 C1 Without C2 C2 C2 C2 Dis C3 C3 C3 C3 C4 C4 C4 C4 C5 C5 C5 C5 T1 T1 T2 T2 T3 T3 T4 T4 T5 T5 Tasks 1-10 T6 T6 T7 T7 T8 T8 T9 T9 T10 T10

  31. Visualizing Adversarial Learning Effect (20-Split miniImageNet) w. Discriminator w/o Discriminator Task Shared Private Shared Private Number Task 20 C1 C1 C1 C1 Without C2 C2 C2 C2 Dis C3 C3 C3 C3 C4 C4 C4 C4 C5 C5 C5 C5 T1 T1 T2 T2 T3 T3 T4 T4 T5 T5 Tasks 1-10 T6 T6 T7 T7 T8 T8 T9 T9 T10 T10

Recommend

SECURITY, ADVERSARIAL SECURITY, ADVERSARIAL LEARNING, AND PRIVACY LEARNING, AND PRIVACY

SECURITY, ADVERSARIAL SECURITY, ADVERSARIAL LEARNING, AND PRIVACY LEARNING, AND PRIVACY

SECURITY, ADVERSARIAL SECURITY, ADVERSARIAL LEARNING, AND PRIVACY LEARNING, AND PRIVACY Christian Kaestner with slides from Eunsuk Kang Required reading: Hulten, Geoff. "Building Intelligent Systems: A Guide to Machine Learning

1.95k views • 113 slides
Continual / Lifelong Learning III: SupSup - Supermasks in Superposition Presenters: Akshata/Zifan

Continual / Lifelong Learning III: SupSup - Supermasks in Superposition Presenters: Akshata/Zifan

CS 839 Special Topics in AI: Deep Learning Fall 2020 Continual / Lifelong Learning III: SupSup - Supermasks in Superposition Presenters: Akshata/Zifan Scribes: Akshata/Zifan 1 Background Continual learning refers to the ability of learning

225 views • 11 slides
Adversarial Learning Bounds for Linear Classes and Neural Nets Understanding Adversarial Learning

Adversarial Learning Bounds for Linear Classes and Neural Nets Understanding Adversarial Learning

Adversarial Learning Bounds for Linear Classes and Neural Nets Understanding Adversarial Learning through Rademacher Complexity Pranjal Awasthi, Natalie Frank, Mehryar Mohri Google Research & Courant Institute August 14, 2020 1 / 17

397 views • 17 slides
Deep Adversarial Learning for NLP 9:00 10:30 Introduction and Adversarial Training, GANs

Deep Adversarial Learning for NLP 9:00 10:30 Introduction and Adversarial Training, GANs

Deep Adversarial Learning for NLP 9:00 10:30 Introduction and Adversarial Training, GANs William Wang 10:30 11:00 Break - 11:00 12:15 Adversarial Examples Sameer Singh 12:15 12:30 Conclusions and Question Answering William

1.75k views • 105 slides
Continuum A Platform for Cost-Aware, Low-Latency Continual Learning Huangshi Tian, Minchen Yu,

Continuum A Platform for Cost-Aware, Low-Latency Continual Learning Huangshi Tian, Minchen Yu,

Continuum A Platform for Cost-Aware, Low-Latency Continual Learning Huangshi Tian, Minchen Yu, Wei Wang @ HKUST Oct 11, 2018 1 Continual/Online vs. Batch/Offline Learning When fresh data arrive, offline / batch offline learning trains model

618 views • 31 slides
Adversarial Approaches to Bayesian Learning and Bayesian Approaches to Adversarial Robustness

Adversarial Approaches to Bayesian Learning and Bayesian Approaches to Adversarial Robustness

Adversarial Approaches to Bayesian Learning and Bayesian Approaches to Adversarial Robustness Ian Goodfellow, OpenAI Research Scientist NIPS 2016 Workshop on Bayesian Deep Learning Barcelona, 2016-12-10 Speculation on Three Topics Can we

769 views • 21 slides
Friendly Adversarial Training: Attacks Which Do Not Kill Training Make Adversarial Learning

Friendly Adversarial Training: Attacks Which Do Not Kill Training Make Adversarial Learning

Friendly Adversarial Training: Attacks Which Do Not Kill Training Make Adversarial Learning Stronger Jingfeng Zhang 1 * , Xilie Xu 2* , Bo Han 34 , Gang Niu 4 , Lichen Cui 5 , Masashi Sugiyama 46 , and Mohan Kankanhalli 1 1 Department of Computer

376 views • 14 slides
AdVersarial: Perceptual Ad Blocking meets Adversarial Machine Learning Florian Tramr November

AdVersarial: Perceptual Ad Blocking meets Adversarial Machine Learning Florian Tramr November

AdVersarial: Perceptual Ad Blocking meets Adversarial Machine Learning Florian Tramr November 14 th 2019 Joint work with Pascal Dupr, Gili Rusak, Giancarlo Pellegrino and Dan Boneh The Future of Ad-Blocking easylist.txt markup

612 views • 23 slides
CSC321 Lecture 22: Adversarial Learning Roger Grosse Roger Grosse CSC321 Lecture 22: Adversarial

CSC321 Lecture 22: Adversarial Learning Roger Grosse Roger Grosse CSC321 Lecture 22: Adversarial

CSC321 Lecture 22: Adversarial Learning Roger Grosse Roger Grosse CSC321 Lecture 22: Adversarial Learning 1 / 26 Overview Two topics for today: Adversarial examples: examples carefully crafted to cause an undesirable behavior (e.g.

412 views • 26 slides
Generative Adversarial Nets(GANs) Troy Cary and Chenzhi Zhao A generative adversarial net is

Generative Adversarial Nets(GANs) Troy Cary and Chenzhi Zhao A generative adversarial net is

Generative Adversarial Nets(GANs) Troy Cary and Chenzhi Zhao A generative adversarial net is a type of neural net, used in deep learning/machine learning problems The goal of a GAN is to train two simultaneous models: a generative model

441 views • 18 slides
Standards for all: Work ethic based on continual improvement Respect Teaching and learning

Standards for all: Work ethic based on continual improvement Respect Teaching and learning

Standards for all: Work ethic based on continual improvement Respect Teaching and learning Character Detail and improvement. Effort as a separate entity Internal communication Poise Abnormal concentration Democratic Pace Coaching

281 views • 25 slides
Learning Universal Adversarial Perturbations with Generative Models Jamie Hayes & George

Learning Universal Adversarial Perturbations with Generative Models Jamie Hayes & George

Learning Universal Adversarial Perturbations with Generative Models Jamie Hayes & George Danezis UCL Adversarial examples transfer between different models. An adversarial example crafted against one model will generally fool other models.

515 views • 18 slides
Policy Consolidation for Continual Reinforcement Learning Christos Kaplanis 1 , Murray Shanahan 1,2

Policy Consolidation for Continual Reinforcement Learning Christos Kaplanis 1 , Murray Shanahan 1,2

Policy Consolidation for Continual Reinforcement Learning Christos Kaplanis 1 , Murray Shanahan 1,2 and Claudia Clopath 1 1 Imperial College London, 2 DeepMind 11th June 2019 Motivation Motivation Catastrophic Forgetting in Artificial Neural

811 views • 17 slides
Brain-like replay for continual learning with artificial neural networks Gido M van de Ven, Hava

Brain-like replay for continual learning with artificial neural networks Gido M van de Ven, Hava

Brain-like replay for continual learning with artificial neural networks Gido M van de Ven, Hava T Siegelmann, Andreas S Tolias Bridging AI and Cognitive Science workshop (ICLR 2020) Catastrophic forgetting in neural networks When a

452 views • 16 slides
Controllable Invariance through Adversarial Feature Learning Qizhe Xie, Zihang Dai, Yulun Du,

Controllable Invariance through Adversarial Feature Learning Qizhe Xie, Zihang Dai, Yulun Du,

Controllable Invariance through Adversarial Feature Learning Qizhe Xie, Zihang Dai, Yulun Du, Eduard Hovy, Graham Neubig Carnegie Mellon University Language Technologies Institute NIPS 2017 Outline Introduction Introduction Adversarial

308 views • 11 slides
Vulnerability of machine learning models to adversarial examples Petra Vidnerov Institute of

Vulnerability of machine learning models to adversarial examples Petra Vidnerov Institute of

Vulnerability of machine learning models to adversarial examples Petra Vidnerov Institute of Computer Science The Czech Academy of Sciences Hora Informaticae 2016 Outline Introduction Works on adversarial examples Our work Genetic

855 views • 46 slides
Adversarial Examples and Adversarial Training Innova&ve Technology Leader program January 22

Adversarial Examples and Adversarial Training Innova&ve Technology Leader program January 22

Adversarial Examples and Adversarial Training Innova&ve Technology Leader program January 22 nd 2018 Florian Tramr Stanford Deep Learning is Super Smart! 2 Is it really? + . 007 = Im sure this Im certain this is a panda is

452 views • 12 slides
Adversarial Domain Adaptation and Adversarial Robustness Judy Hoffman + = Big Deep success

Adversarial Domain Adaptation and Adversarial Robustness Judy Hoffman + = Big Deep success

Adversarial Domain Adaptation and Adversarial Robustness Judy Hoffman + = Big Deep success data learning Benchmark Performance 100 95 Accuracy 90 85 Millions of Images 80 Deep models 75 Challenge to recognize 1000

1.2k views • 60 slides
Shrinking and Exploring David Evans University of Virginia Adversarial Search Spaces ARO

Shrinking and Exploring David Evans University of Virginia Adversarial Search Spaces ARO

evadeML. L.org Shrinking and Exploring David Evans University of Virginia Adversarial Search Spaces ARO Workshop on Adversarial Learning Stanford, 14 Sept 2017 Weilin Xu Yanjun Qi Machine Learning is Eating Computer Science 1 Security

552 views • 54 slides
A CONTINUAL LEARNING APPROACH FOR LOCAL LEVEL ENVIRONMENTAL MONITORING IN LOW-RESOURCE SETTINGS

A CONTINUAL LEARNING APPROACH FOR LOCAL LEVEL ENVIRONMENTAL MONITORING IN LOW-RESOURCE SETTINGS

A CONTINUAL LEARNING APPROACH FOR LOCAL LEVEL ENVIRONMENTAL MONITORING IN LOW-RESOURCE SETTINGS Arijit Patra Siva Chamarti University of Oxford Motivation: Crowdsourcing environmental monitoring Local monitoring first line of

240 views • 7 slides
Provably Secure Machine Learning Jacob Steinhardt ARO Adversarial Machine Learning Workshop

Provably Secure Machine Learning Jacob Steinhardt ARO Adversarial Machine Learning Workshop

Provably Secure Machine Learning Jacob Steinhardt ARO Adversarial Machine Learning Workshop September 14, 2017 Why Prove Things? Attackers often have more motivation/resources than defenders Heuristic defenses: arms race between attack and

738 views • 52 slides
Adversarial Machine Learning (AML) Somesh Jha University of Wisconsin, Madison Thanks to

Adversarial Machine Learning (AML) Somesh Jha University of Wisconsin, Madison Thanks to

Adversarial Machine Learning (AML) Somesh Jha University of Wisconsin, Madison Thanks to Nicolas Papernot, Ian Goodfellow, and Jerry Zhu for some slides . Machine learning brings social disruption at scale Healthcare Energy Source: Peng and

821 views • 71 slides
Physical Adversarial Examples Alex Kurakin Ian Goodfellow Output STOP Machine Learning

Physical Adversarial Examples Alex Kurakin Ian Goodfellow Output STOP Machine Learning

Physical Adversarial Examples Alex Kurakin Ian Goodfellow Output STOP Machine Learning Training Examples Hidden units / BICYCLE features CAR PEDESTRIA N Parameters Input ImageNet (Russakovsky et al 2015) Adversarial Examples: Images

369 views • 19 slides
LAB MEETING: A Connection Between Generative Adversarial Networks, Inverse Reinforcement Learning

LAB MEETING: A Connection Between Generative Adversarial Networks, Inverse Reinforcement Learning

LAB MEETING: A Connection Between Generative Adversarial Networks, Inverse Reinforcement Learning and Energy-Based models Suwon Suh POSTECH MLG Feb, 13, 2017 Goal Understanding Basic Models 1) Generative Adversarial Networks (GAN) 2)

722 views • 12 slides

More recommend