Abstract
Continual learning is an approach in machine learning that aims to learn different tasks sequentially, still performing well on all of them. This manner is akin to human learning. However, continual learning faces a significant challenge known as catastrophic forgetting. This refers to as a decrease in the model’s performance on previously learned tasks when learning a new task. Memory-based replay method is one approach that has been proven effective in addressing this issue. After completing each task, the model stores a small amount of data to combine with new data for training an encountering task. This approach is associated with the size of the memory buffer and data security concerns. In this paper, instead of storing actual data points, we only store prototypes representing classes in learned tasks. To this end, we also employ two techniques, i.e. Online Prototype Equilibrium (OPE) and Adaptive Prototypical Feedback (APF) to enhance the quality of prototypes’ hidden representation. Furthermore, to enhance accurate classification, we do not use a single shared head for all classes. Instead, for each task, we add a within-task prediction head and a task-ID prediction head. Experimental results on benchmark datasets demonstrate that our method outperforms several state-of-the-art methods in terms of well-studied average accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
McCloskey, M., Cohen, N.J.: Catastrophic interference in connectionist networks: the sequential learning problem. In: Psychology of Learning and Motivation, vol. 24, pp. 109–165. Academic Press (1989)
Aljundi, R., Babiloni, F., Elhoseiny, M., Rohrbach, M., Tuytelaars, T.: Memory aware synapses: learning what (not) to forget. In: Proceedings of the European conference on computer vision (ECCV), pp. 139–154 (2018)
Serra, J., Suris, D., Miron, M., Karatzoglou, A.: Overcoming catastrophic forgetting with hard attention to the task. In: International Conference on Machine Learning, pp. 4548–4557. PMLR, July 2018
Mai, Z., Li, R., Jeong, J., Quispe, D., Kim, H., Sanner, S.: Online continual learning in image classification: an empirical survey. Neurocomputing 469, 28–51 (2022)
Chrysakis, A., Moens, M.F.: Online continual learning from imbalanced data. In: International Conference on Machine Learning, pp. 1952–1961. PMLR, November 2020
He, J., Mao, R., Shao, Z., Zhu, F.: Incremental learning in online scenario. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13926–13935 (2020)
Asadi, N., Davari, M., Mudur, S., Aljundi, R., Belilovsky, E.: Prototype-sample relation distillation: towards replay-free continual learning. In: International Conference on Machine Learning, pp. 1093–1106. PMLR, July 2023
Chaudhry, A., Ranzato, M.A., Rohrbach, M., Elhoseiny, M.: Efficient lifelong learning with a-gem. arXiv preprint arXiv:1812.00420 (2018)
Caccia, M., et al.: Online fast adaptation and knowledge accumulation: a new approach to continual learning. arXiv preprint arXiv:2003.05856 (2020)
Wei, Y., Ye, J., Huang, Z., Zhang, J., Shan, H.: Online prototype learning for online continual learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 18764–18774 (2023)
De Lange, M., Tuytelaars, T.: Continual prototype evolution: learning online from non-stationary data streams. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8250–8259 (2021)
Davari, M., Asadi, N., Mudur, S., Aljundi, R., Belilovsky, E.: Probing representation forgetting in supervised and unsupervised continual learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16712–16721 (2022)
Fang, Z., Wang, J., Wang, L., Zhang, L., Yang, Y., Liu, Z.: Seed: Self-supervised distillation for visual representation. arXiv preprint arXiv:2101.04731 (2021)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)
Guo, Y., Liu, B., Zhao, D.: Online continual learning through mutual information maximization. In: International Conference on Machine Learning, pp. 8109–8126. PMLR, June 2022
Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2935–2947 (2017)
Cha, H., Lee, J., Shin, J.: Co2l: contrastive continual learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9516–9525 (2021)
Kim, G., Xiao, C., Konishi, T., Liu, B.: Learnability and Algorithm for Continual Learning. arXiv preprint arXiv:2306.12646 (2023)
Kim, G., Xiao, C., Konishi, T., Ke, Z., Liu, B.: A theoretical study on solving continual learning. Adv. Neural. Inf. Process. Syst. 35, 5065–5079 (2022)
Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: icarl: incremental classifier and representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2001–2010 (2017)
Buzzega, P., Boschini, M., Porrello, A., Abati, D., Calderara, S.: Dark experience for general continual learning: a strong, simple baseline. Adv. Neural. Inf. Process. Syst. 33, 15920–15930 (2020)
Zhu, F., Zhang, X.Y., Wang, C., Yin, F., Liu, C.L.: Prototype augmentation and self-supervision for incremental learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5871–5880 (2021)
Aljundi, R., Lin, M., Goujaud, B., Bengio, Y.: Gradient based sample selection for online continual learning. Advances in neural information processing systems, 32 (2019)
Chaudhry, A., et al.: On tiny episodic memories in continual learning. arXiv preprint arXiv:1902.10486 (2019)
Aljundi, R., et al.: Online continual learning with maximal interfered retrieval. In: Advances in Neural Information Processing Systems, vol. 32 (2019). 1, 2, 5, 6, 7
Prabhu, A., Torr, P.H.S., Dokania, P.K.: GDumb: a simple approach that questions our progress in continual learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 524–540. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58536-5_31
Shim, D., Mai, Z., Jeong, J., Sanner, S., Kim, H., Jang, J.: Online class-incremental continual learning with adversarial shapley value. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, No. 11, pp. 9630–9638, May 2021
Mai, Z., Li, R., Kim, H., Sanner, S.: Supervised contrastive replay: revisiting the nearest class mean classifier in online class-incremental continual learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3589–3599 (2021)
Gu, Y., Yang, X., Wei, K., Deng, C.: Not just selection, but exploration: online class-incremental continual learning via dual view consistency. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7442-7451 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Pham Thi, QT., Nguyen, DH., Dang, T.H., Le, DT., Nguyen, TT., Ha, QT. (2024). Towards Robust Continual Learning: A Multi-Head Approach with Online Prototype Equilibrium and Adaptive Prototypical Feedback. In: Nguyen, N.T., et al. Intelligent Information and Database Systems. ACIIDS 2024. Lecture Notes in Computer Science(), vol 14796. Springer, Singapore. https://doi.org/10.1007/978-981-97-4985-0_22
Download citation
DOI: https://doi.org/10.1007/978-981-97-4985-0_22
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-4984-3
Online ISBN: 978-981-97-4985-0
eBook Packages: Computer ScienceComputer Science (R0)