Selecting Useful Knowledge from Previous Tasks for Future Learning in a Single Network

Continual learning can learn new tasks incrementally while avoiding catastrophic forgetting. Recent work has shown that packing multiple tasks into a single network incrementally by iterative pruning and re-training network is a promising method. We build upon this idea and propose an improved version of PackNet. Specifically, we propose a novel gradient-based threshold method to reuse the knowledge of the previous tasks selectively when learning new tasks. Our experiments on a variety of classification tasks and different network architectures demonstrate that our method obtains competitive results when compared to PackNet.

[1]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[2]  Byoung-Tak Zhang,et al.  Overcoming Catastrophic Forgetting by Incremental Moment Matching , 2017, NIPS.

[3]  Chrisantha Fernando,et al.  PathNet: Evolution Channels Gradient Descent in Super Neural Networks , 2017, ArXiv.

[4]  Marc'Aurelio Ranzato,et al.  Continual Learning with Tiny Episodic Memories , 2019, ArXiv.

[5]  Benjamin F. Grewe,et al.  Continual learning with hypernetworks , 2019, ICLR.

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

[7]  Yandong Guo,et al.  Large Scale Incremental Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Razvan Pascanu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[9]  Alexandros Kalousis,et al.  Continual Classification Learning Using Generative Models , 2018, NIPS 2018.

[10]  Joost van de Weijer,et al.  Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

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

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

[13]  Shan Yu,et al.  Continual learning of context-dependent processing in neural networks , 2018, Nature Machine Intelligence.

[14]  Barbara Caputo,et al.  Adding New Tasks to a Single Network with Weight Trasformations using Binary Masks , 2018, ECCV Workshops.

[15]  Rama Chellappa,et al.  Learning Without Memorizing , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  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.

[17]  David Isele,et al.  Selective Experience Replay for Lifelong Learning , 2018, AAAI.

[18]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[19]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Alexandros Karatzoglou,et al.  Overcoming Catastrophic Forgetting with Hard Attention to the Task , 2018 .

[21]  David Filliat,et al.  Continual Learning for Robotics , 2019, Inf. Fusion.

[22]  Pietro Perona,et al.  The Caltech-UCSD Birds-200-2011 Dataset , 2011 .

[23]  Tinne Tuytelaars,et al.  Online Continual Learning with Maximally Interfered Retrieval , 2019, ArXiv.

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

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

[26]  Botond Cseke,et al.  Continual Learning with Bayesian Neural Networks for Non-Stationary Data , 2020, ICLR.

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

[28]  Nojun Kwak,et al.  StackNet: Stacking feature maps for Continual learning , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[29]  Surya Ganguli,et al.  Continual Learning Through Synaptic Intelligence , 2017, ICML.

[30]  Stefan Wermter,et al.  Continual Lifelong Learning with Neural Networks: A Review , 2019, Neural Networks.

[31]  Richard Socher,et al.  Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting , 2019, ICML.

[32]  Fahad Shahbaz Khan,et al.  iTAML: An Incremental Task-Agnostic Meta-learning Approach , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Lifeng Sun,et al.  Adversarial Feature Alignment: Avoid Catastrophic Forgetting in Incremental Task Lifelong Learning , 2019, Neural Computation.

[34]  Jonathan Krause,et al.  3D Object Representations for Fine-Grained Categorization , 2013, 2013 IEEE International Conference on Computer Vision Workshops.

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

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

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

[38]  Eric Eaton,et al.  ELLA: An Efficient Lifelong Learning Algorithm , 2013, ICML.

[39]  Matthew B. Blaschko,et al.  Encoder Based Lifelong Learning , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

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

[41]  Andrew Zisserman,et al.  Automated Flower Classification over a Large Number of Classes , 2008, 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing.

[42]  Christoph H. Lampert,et al.  iCaRL: Incremental Classifier and Representation Learning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[44]  Matthias De Lange,et al.  Continual learning: A comparative study on how to defy forgetting in classification tasks , 2019, ArXiv.