Abstract
Continual learning is a crucial ability for learning systems that have to adapt to changing data distributions, without reducing their performance in what they have already learned. Rehearsal methods offer a simple countermeasure to help avoid this catastrophic forgetting which frequently occurs in dynamic situations and is a major limitation of machine learning models. These methods continuously train neural networks using a mix of data both from the stream and from a rehearsal buffer, which maintains past training samples. Although the rehearsal approach is reasonable and simple to implement, its effectiveness and efficiency is significantly affected by several hyperparameters such as the number of training iterations performed at each step, the choice of learning rate, and the choice on whether to retrain the agent at each step. These options are especially important in resource-constrained environments commonly found in online continual learning for image analysis. This work evaluates several rehearsal training strategies for continual online learning and proposes the combined use of a drift detector that decides on (a) when to train using data from the buffer and the online stream, and (b) how to train, based on a combination of heuristics. Experiments on the MNIST and CIFAR-10 image classification datasets demonstrate the effectiveness of the proposed approach over baseline training strategies at a fraction of the computational cost.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bottou, L., Bousquet, O.: The tradeoffs of large-scale learning. In: Optimization for Machine Learning, p. 351 (2011)
Chaudhry, A., et al.: Continual Learning with Tiny Episodic Memories. CoRR, vol. abs/1902.10486 (2019)
Delange, M., et al.: A continual learning survey: defying forgetting in classification tasks. IEEE Trans. Pattern Anal. Mach. Intell., 1 (2021). https://doi.org/10.1109/TPAMI.2021.3057446
Demosthenous, G., Vassiliades, V.: Continual Learning on the Edge with TensorFlow Lite. arXiv preprint arXiv:2105.01946 (2021)
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)
He, K., Zhang, X., Ren, S., Sun, J.: Deep Residual Learning for Image Recognition. arXiv [cs.CV] (2015)
Krizhevsky, A.: Learning multiple layers of features from tiny images (2009)
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Li, Z., Hoiem, D.: Learning without Forgetting. CoRR, vol. abs/1606.09282 (2016)
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)
Milan, K., Veness, J., Kirkpatrick, J., Hassabis, D., Koop, A., Bowling, M.: The forget-me-not process. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, pp. 3709–3717 (2016)
Pellegrini, L., Graffieti, G., Lomonaco, V., Maltoni, D.: Latent Replay for Real-Time Continual Learning. CoRR, vol. abs/1912.01100 (2019)
Pellegrini, L., Lomonaco, V., Graffieti, G., Maltoni, D.: Continual Learning at the Edge: Real-Time Training on Smartphone Devices. arXiv preprint arXiv:2105.13127 (2021)
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)
Rolnick, D., Ahuja, A., Schwarz, J., Lillicrap, T.P., Wayne, G.: Experience Replay for Continual Learning. CoRR, vol. abs/1811.11682 (2018)
Ross, G.J., Adams, N.M., Tasoulis, D.K., Hand, D.J.: Exponentially weighted moving average charts for detecting concept drift. Pattern Recogn. Lett. 33(2), 191–198 (2012)
Wiewel, F., Yang, B.: Entropy-based sample selection for online continual learning. In: 28th European Signal Proceedings Conference (EUSIPCO), pp. 1477–1481 (2021)
Widmer, G., Kubat, M.: Learning in the presence of concept drift and hidden contexts. Mach. Learn. 23(1), 69–101 (1996)
Acknowledgment
This work is supported by the “TEACHING” project that has received funding from the European Union’s Horizon 2020 research and innovation programme under the grant agreement No 871385. The work reflects only the author’s view and the EU Agency is not responsible for any use that may be made of the information it contains.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Davalas, C., Michail, D., Diou, C., Varlamis, I., Tserpes, K. (2022). Computationally Efficient Rehearsal for Online Continual Learning. In: Sclaroff, S., Distante, C., Leo, M., Farinella, G.M., Tombari, F. (eds) Image Analysis and Processing – ICIAP 2022. ICIAP 2022. Lecture Notes in Computer Science, vol 13233. Springer, Cham. https://doi.org/10.1007/978-3-031-06433-3_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-06433-3_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06432-6
Online ISBN: 978-3-031-06433-3
eBook Packages: Computer ScienceComputer Science (R0)