Skip to main content

Marginal Replay vs Conditional Replay for Continual Learning

  • Conference paper
  • First Online:
Artificial Neural Networks and Machine Learning – ICANN 2019: Deep Learning (ICANN 2019)

Abstract

We present a new replay-based method of continual classification learning that we term “conditional replay” which generates samples and labels together by sampling from a distribution conditioned on the class. We compare conditional replay to another replay-based continual learning paradigm (which we term “marginal replay”) that generates samples independently of their class and assigns labels in a separate step. The main improvement in conditional replay is that labels for generated samples need not be inferred, which reduces the margin for error in complex continual classification learning tasks. We demonstrate the effectiveness of this approach using novel and standard benchmarks constructed from MNIST and FashionMNIST data, and compare to the regularization-based elastic weight consolidation (EWC) method [17, 34].

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Aljundi, R., Babiloni, F., Elhoseiny, M., Rohrbach, M., Tuytelaars, T.: Memory aware synapses: learning what (not) to forget. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 144–161. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01219-9_9

    Chapter  Google Scholar 

  2. Aljundi, R., Chakravarty, P., Tuytelaars, T.: Expert gate lifelong learning with a network of experts. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3366–3375 (2017)

    Google Scholar 

  3. Aljundi, R., Rohrbach, M., Tuytelaars, T.: Selfless sequential learning. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=Bkxbrn0cYX

  4. Chaudhry, A., Dokania, P.K., Ajanthan, T., Torr, P.H.S.: Riemannian walk for incremental learning: understanding forgetting and intransigence. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 556–572. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01252-6_33

    Chapter  Google Scholar 

  5. Fernando, C., et al.: PathNet: evolution channels gradient descent in super neural networks. arXiv preprint arXiv:1701.08734 (2017)

  6. French, R.: Catastrophic forgetting in connectionist networks. Trends Cognit. Sci. 3(4), 128 (1999)

    Article  Google Scholar 

  7. Gepperth, A., Wiech, F.: Simplified computation and interpretation of fisher matrices in incremental learning with deep neural networks. In: ICANN (2019, Submitted)

    Google Scholar 

  8. Gepperth, A., Hammer, B.: Incremental learning algorithms and applications. In: European Symposium on Artificial Neural Networks (ESANN) (2016)

    Google Scholar 

  9. Gepperth, A., Karaoguz, C.: A bio-inspired incremental learning architecture for applied perceptual problems. Cognit. Comput. 8(5), 924–934 (2016). https://doi.org/10.1007/s12559-016-9389-5

    Article  Google Scholar 

  10. Goodfellow, I., et al.: Generative adversarial nets. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 27, pp. 2672–2680. Curran Associates, Inc. (2014). http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf

  11. Goodfellow, I.J., Mirza, M., Xiao, D., Courville, A., Bengio, Y.: An empirical investigation of catastrophic forgetting in gradient-based neural networks (2013). https://doi.org/10.1088/1751-8113/44/8/085201. http://arxiv.org/abs/1312.6211

    Article  MathSciNet  Google Scholar 

  12. Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors, pp. 1–18 (2012). arXiv:1207.0580

  13. Kamra, N., Gupta, U., Liu, Y.: Deep generative dual memory network for continual learning. ArXiv e-prints, arXiv:1710.10368, October 2017

  14. Kemker, R., Kanan, C.: FearNet: brain-inspired model for incremental learning. arXiv preprint arXiv:1711.10563 (2017)

  15. Kim, H., Kim, S., Lee, J.: Keep and learn: continual learning by constraining the latent space for knowledge preservation in neural networks. CoRR abs/1805.10784 (2018). http://arxiv.org/abs/1805.10784

  16. Kim, H.-E., Kim, S., Lee, J.: Keep and learn: continual learning by constraining the latent space for knowledge preservation in neural networks. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 520–528. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00928-1_59

    Chapter  Google Scholar 

  17. Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks (2016). https://doi.org/10.1073/pnas.1611835114. http://arxiv.org/abs/1612.00796

    Article  MathSciNet  Google Scholar 

  18. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning apllied to document recognition (1998). http://ieeexplore.ieee.org/document/726791/#full-text-section

    Article  Google Scholar 

  19. Lee, S.W., Kim, J.H., Jun, J., Ha, J.W., Zhang, B.T.: Overcoming catastrophic forgetting by incremental moment matching. In: Advances in Neural Information Processing Systems, pp. 4655–4665 (2017)

    Google Scholar 

  20. Lesort, T., Goudou, J.F., Filliat, D.: Training discriminative models to evaluate generative ones (2018)

    Google Scholar 

  21. Lesort, T., Caselles-Dupré, H., Garcia- Ortiz, M., Stoian, A., Filliat, D.: Generative models from the perspective of continual learning. arXiv e-prints arXiv:1812.09111, December 2018

  22. Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2935–2947 (2018)

    Article  Google Scholar 

  23. Liu, X., Masana, M., Herranz, L., Van de Weijer, J., Lopez, A.M., Bagdanov, A.D.: Rotate your networks: better weight consolidation and less catastrophic forgetting. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 2262–2268. IEEE (2018)

    Google Scholar 

  24. Mallya, A., Lazebnik, S.: PackNet: adding multiple tasks to a single network by iterative pruning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7765–7773 (2018)

    Google Scholar 

  25. Mirza, M., Osindero, S.: Conditional generative adversarial nets (2014)

    Google Scholar 

  26. Parisi, G.I., Kemker, R., Part, J.L., Kanan, C., Wermter, S.: Continual lifelong learning with neural networks: a review. arXiv preprint arXiv:1802.07569 (2018)

  27. Pfülb, B., Gepperth, A.: A comprehensive, application-oriented study of catastrophic forgetting in DNNS. In: International Conference on Learning Representations (ICLR) (2019, Accepted)

    Google Scholar 

  28. Pfülb, B., Gepperth, A., Abdullah, S., Kilian, A.: Catastrophic forgetting: still a problem for DNNs. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11139, pp. 487–497. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01418-6_48

    Chapter  Google Scholar 

  29. Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: iCaRL: incremental classifier and representation learning. In: Proceedings of the CVPR (2017)

    Google Scholar 

  30. Ren, B., Wang, H., Li, J., Gao, H.: Life-long learning based on dynamic combination model. Appl. Soft Comput. 56, 398–404 (2017)

    Article  Google Scholar 

  31. Rusu, A.A., et al.: Progressive neural networks. arXiv preprint arXiv:1606.04671 (2016)

  32. Serrà, J., Suris, D., Miron, M., Karatzoglou, A.: Overcoming catastrophic forgetting with hard attention to the task. In: The 35th International Conference on Machine Learning (ICML 2018) (2018). https://arxiv.org/abs/1801.01423

  33. Shah, H., Javed, K., Shafait, F.: Distillation techniques for pseudo-rehearsal based incremental learning. arXiv preprint arXiv:1807.02799 (2018)

  34. Shin, H., Lee, J.K., Kim, J., Kim, J.: Continual learning with deep generative replay. In: Advances in Neural Information Processing Systems, pp. 2990–2999 (2017)

    Google Scholar 

  35. Shmelkov, K., Schmid, C., Alahari, K.: Incremental learning of object detectors without catastrophic forgetting. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3400–3409 (2017)

    Google Scholar 

  36. Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems 28, pp. 3483–3491. Curran Associates, Inc. (2015)

    Google Scholar 

  37. Srivastava, R.K., Masci, J., Kazerounian, S., Gomez, F., Schmidhuber, J.: Compete to compute. In: NIPS, pp. 2310–2318 (2013)

    Google Scholar 

  38. Wu, C., Herranz, L., Liu, X., Wang, Y., van de Weijer, J., Raducanu, B.: Memory replay GANs: learning to generate images from new categories without forgetting. arXiv preprint arXiv:1809.02058 (2018)

  39. Wu, Y., et al.: Incremental classifier learning with generative adversarial networks. CoRR abs/1802.00853 (2018). http://arxiv.org/abs/1802.00853

  40. Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms, pp. 1–6 (2017). http://arxiv.org/abs/1708.07747

  41. Yoon, J., Yang, E., Lee, J., Hwang, S.J.: Lifelong learning with dynamically expandable networks. arXiv preprint arXiv:1708.01547 (2017)

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Timothée Lesort .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Lesort, T., Gepperth, A., Stoian, A., Filliat, D. (2019). Marginal Replay vs Conditional Replay for Continual Learning. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds) Artificial Neural Networks and Machine Learning – ICANN 2019: Deep Learning. ICANN 2019. Lecture Notes in Computer Science(), vol 11728. Springer, Cham. https://doi.org/10.1007/978-3-030-30484-3_38

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-30484-3_38

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-30483-6

  • Online ISBN: 978-3-030-30484-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics