Skip to main content

Disentangled Representations for Continual Learning: Overcoming Forgetting and Facilitating Knowledge Transfer

  • Conference paper
  • First Online:
Machine Learning and Knowledge Discovery in Databases. Research Track (ECML PKDD 2024)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 14944))

  • 538 Accesses

Abstract

Achieving knowledge transfer is a new challenge in continual learning, which requires the model to not only overcome catastrophic forgetting but also make full use of the knowledge from multiple tasks to solve a particular task. In this paper, we propose to disentangle representations in continual learning into task-shared and task-specific representations, using shared and task-specific encoders to obtain the corresponding disentangled representations, respectively. However, forgetting persists in the shared encoder, and task encoders are unable to transfer knowledge to each other. In order to overcome forgetting in the shared encoder, we introduce the Fisher mask to limit the update of important parameters of old tasks. Further, a multi-knowledge distillation method is proposed to promote the shared encoder to consolidate the knowledge of all tasks by interacting with task encoders. To facilitate knowledge transfer among task encoders, we select and fuse knowledge from the task encoder of each old task to apply to the new task. Experiments show that our proposed method achieves performance beyond state-of-the-art baselines using a smaller network without replay data.

Z. Xu and Q. Qin—Equal contribution.

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

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Belouadah, E., Popescu, A.: Il2m: class incremental learning with dual memory. In: ICCV, pp. 583–592 (2019)

    Google Scholar 

  2. Buzzega, P., Boschini, M., Porrello, A., Abati, D., Calderara, S.: Dark experience for general continual learning: a strong, simple baseline. In: NIPS, vol. 33, pp. 15920–15930 (2020)

    Google Scholar 

  3. Castro, F.M., Marín-Jiménez, M.J., Guil, N., Schmid, C., Alahari, K.: End-to-end incremental learning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 241–257. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01258-8_15

    Chapter  Google Scholar 

  4. Chaudhry, A., Ranzato, M., Rohrbach, M., Elhoseiny, M.: Efficient lifelong learning with a-gem. In: ICLR (2019)

    Google Scholar 

  5. Chaudhry, A., et al.: Continual learning with tiny episodic memories. arXiv preprint arXiv:1902.10486 2019 (2019)

  6. Chen, X., Chang, X.: Dynamic residual classifier for class incremental learning. In: ICCV, pp. 18743–18752 (2023)

    Google Scholar 

  7. Dhar, P., Singh, R.V., Peng, K.C., Wu, Z., Chellappa, R.: Learning without memorizing. In: CVPR, pp. 5138–5146 (2019)

    Google Scholar 

  8. Ebrahimi, S., Meier, F., Calandra, R., Darrell, T., Rohrbach, M.: Adversarial continual learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 386–402. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58621-8_23

    Chapter  Google Scholar 

  9. Feng, T., Wang, M., Yuan, H.: Overcoming catastrophic forgetting in incremental object detection via elastic response distillation. In: CVPR, pp. 9427–9436 (2022)

    Google Scholar 

  10. Hayes, T.L., Kafle, K., Shrestha, R., Acharya, M., Kanan, C.: REMIND your neural network to prevent catastrophic forgetting. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 466–483. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58598-3_28

    Chapter  Google Scholar 

  11. Hu, W., et al.: Overcoming catastrophic forgetting for continual learning via model adaptation. In: ICLR (2019)

    Google Scholar 

  12. Jeeveswaran, K., Bhat, P.S., Zonooz, B., Arani, E.: BIRT: bio-inspired replay in vision transformers for continual learning. In: ICML, pp. 14817–14835. PMLR (2023)

    Google Scholar 

  13. Kemker, R., Kanan, C.: FearNet: brain-inspired model for incremental learning. In: ICLR (2018)

    Google Scholar 

  14. Kirkpatrick, J., et al.: Overcoming Catastrophic Forgetting in Neural Networks. vol. 114, pp. 3521–3526. National Acad Sciences (2017)

    Google Scholar 

  15. Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. In: Handbook of Systemic Autoimmune Diseases, vol. 1, no. 4 (2009)

    Google Scholar 

  16. Lin, H., Zhang, B., Feng, S., Li, X., Ye, Y.: PCR: proxy-based contrastive replay for online class-incremental continual learning. In: CVPR, pp. 24246–24255 (2023)

    Google Scholar 

  17. Lin, S., Yang, L., Fan, D., Zhang, J.: TRGP: trust region gradient projection for continual learning. In: ICLR (2021)

    Google Scholar 

  18. Lin, S., Yang, L., Fan, D., Zhang, J.: Beyond not-forgetting: continual learning with backward knowledge transfer. In: NIPS, vol. 35, pp. 16165–16177 (2022)

    Google Scholar 

  19. Liu, Y., Su, Y., Liu, A.A., Schiele, B., Sun, Q.: Mnemonics training: multi-class incremental learning without forgetting. In: CVPR, pp. 12245–12254 (2020)

    Google Scholar 

  20. Lopez-Paz, D., Ranzato, M.: Gradient episodic memory for continual learning. In: NIPS, vol. 30 (2017)

    Google Scholar 

  21. McCloskey, M., Cohen, N.J.: Catastrophic interference in connectionist networks: the sequential learning problem. In: Psychology of Learning & Motivation, vol. 24 (1989)

    Google Scholar 

  22. Ostapenko, O., Puscas, M., Klein, T., Jahnichen, P., Nabi, M.: Learning to remember: a synaptic plasticity driven framework for continual learning. In: CVPR, pp. 11321–11329 (2019)

    Google Scholar 

  23. Qin, Q., Hu, W., Peng, H., Zhao, D., Liu, B.: BNS: building network structures dynamically for continual learning. In: NIPS, vol. 34, pp. 20608–20620 (2021)

    Google Scholar 

  24. Rolnick, D., Ahuja, A., Schwarz, J., Lillicrap, T., Wayne, G.: Experience replay for continual learning. In: NIPS, vol. 32 (2019)

    Google Scholar 

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

  26. Saha, G., Garg, I., Roy, K.: Gradient projection memory for continual learning. In: ICLR (2020)

    Google Scholar 

  27. Serra, J., Suris, D., Miron, M., Karatzoglou, A.: Overcoming catastrophic forgetting with hard attention to the task. In: ICML, pp. 4548–4557. PMLR (2018)

    Google Scholar 

  28. Sun, W., Li, Q., Zhang, J., Wang, W., Geng, Y.A.: Decoupling learning and remembering: a bilevel memory framework with knowledge projection for task-incremental learning. In: CVPR, pp. 20186–20195 (2023)

    Google Scholar 

  29. Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. In: NIPS, vol. 29 (2016)

    Google Scholar 

  30. Wang, F.Y., et al.: Beef: bi-compatible class-incremental learning via energy-based expansion and fusion. In: ICLR (2022)

    Google Scholar 

  31. Wang, F.Y., Zhou, D.W., Ye, H.J., Zhan, D.C.: Foster: feature boosting and compression for class-incremental learning. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13685, pp. 398–414. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19806-9_23

  32. Wang, L., Zhang, X., Su, H., Zhu, J.: A comprehensive survey of continual learning: theory, method and application. IEEE Trans. Pattern Anal. Mach. Intell. 46, 5362–5383 (2024)

    Article  Google Scholar 

  33. Wu, C., Herranz, L., Liu, X., van de Weijer, J., Raducanu, B., et al.: Memory replay gans: Learning to generate new categories without forgetting. In: NIPS, pp. 5962–5972 (2018)

    Google Scholar 

  34. Yan, S., Xie, J., He, X.: DER: dynamically expandable representation for class incremental learning. In: CVPR, pp. 3014–3023 (2021)

    Google Scholar 

  35. Yoon, J., Kim, S., Yang, E., Hwang, S.J.: Scalable and order-robust continual learning with additive parameter decomposition. In: ICLR (2020)

    Google Scholar 

  36. Zenke, F., Poole, B., Ganguli, S.: Continual learning through synaptic intelligence. In: ICML, pp. 3987–3995. PMLR (2017)

    Google Scholar 

  37. Zhao, Z., et al.: Rethinking gradient projection continual learning: stability/plasticity feature space decoupling. In: CVPR, pp. 3718–3727 (2023)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding authors

Correspondence to Bing Liu or Dongyan Zhao .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Xu, Z., Qin, Q., Liu, B., Zhao, D. (2024). Disentangled Representations for Continual Learning: Overcoming Forgetting and Facilitating Knowledge Transfer. In: Bifet, A., Davis, J., Krilavičius, T., Kull, M., Ntoutsi, E., Žliobaitė, I. (eds) Machine Learning and Knowledge Discovery in Databases. Research Track. ECML PKDD 2024. Lecture Notes in Computer Science(), vol 14944. Springer, Cham. https://doi.org/10.1007/978-3-031-70359-1_9

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-70359-1_9

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-70358-4

  • Online ISBN: 978-3-031-70359-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics