Abstract
This paper presents SPeCiaL: a method for unsupervised pretraining of representations tailored for continual learning. Our approach devises a meta-learning objective that differentiates through a sequential learning process. Specifically, we train a linear model over the representations to match different augmented views of the same image together, each view presented sequentially. The linear model is then evaluated on both its ability to classify images it just saw, and also on images from previous iterations. This gives rise to representations that favor quick knowledge retention with minimal forgetting. We evaluate SPeCiaL in the Continual Few-Shot Learning setting, and show that it can match or outperform other supervised pretraining approaches.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Achille, A., et al.: Life-long disentangled representation learning with cross-domain latent homologies. arXiv preprint arXiv:1808.06508 (2018)
Aljundi, R., et al.: Online continual learning with maximally interfered retrieval. arXiv preprint arXiv:1908.04742 (2019)
Aljundi, R., Lin, M., Goujaud, B., Bengio, Y.: Gradient based sample selection for online continual learning. arXiv preprint arXiv:1903.08671 (2019)
Aljundi, R., Rohrbach, M., Tuytelaars, T.: Selfless sequential learning. arXiv preprint arXiv:1806.05421 (2018)
Antoniou, A., Storkey, A.: Assume, augment and learn: Unsupervised few-shot meta-learning via random labels and data augmentation. arXiv preprint arXiv:1902.09884 (2019)
Assran, M., Ballas, N., Castrejon, L., Rabbat, M.: Supervision accelerates pre-training in contrastive semi-supervised learning of visual representations. arXiv preprint arXiv:2006.10803 (2020)
Beaulieu, S., et al.: Learning to continually learn. arXiv preprint arXiv:2002.09571 (2020)
Bertugli, A., Vincenzi, S., Calderara, S., Passerini, A.: Generalising via meta-examples for continual learning in the wild. arXiv preprint arXiv:2101.12081 (2021)
Caccia, L., Belilovsky, E., Caccia, M., Pineau, J.: Online learned continual compression with adaptive quantization modules. In: International Conference on Machine Learning, pp. 1240–1250. PMLR (2020)
Caccia, M., et al.: Online fast adaptation and knowledge accumulation: a new approach to continual learning. arXiv preprint arXiv:2003.05856 (2020)
Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. arXiv preprint arXiv:2006.09882 (2020)
Chaudhry, A., Ranzato, M., Rohrbach, M., Elhoseiny, M.: Efficient lifelong learning with a-gem. arXiv preprint arXiv:1812.00420 (2018)
Chaudhry, A., et al.: Continual learning with tiny episodic memories (2019)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597–1607. PMLR (2020)
Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, pp. 1126–1135. PMLR (2017)
French, R.M.: Using semi-distributed representations to overcome catastrophic forgetting in connectionist networks. In: Proceedings of the 13th Annual Cognitive Science Society Conference, vol. 1, pp. 173–178 (1991)
Gupta, G., Yadav, K., Paull, L.: Look-ahead meta learning for continual learning. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 11588–11598. Curran Associates, Inc. (2020). https://proceedings.neurips.cc/paper/2020/file/85b9a5ac91cd629bd3afe396ec07270a-Paper.pdf
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729–9738 (2020)
Hsu, K., Levine, S., Finn, C.: Unsupervised learning via meta-learning. arXiv preprint arXiv:1810.02334 (2018)
Javed, K., White, M.: Meta-learning representations for continual learning. arXiv preprint arXiv:1905.12588 (2019)
Khodadadeh, S., Bölöni, L., Shah, M.: Unsupervised meta-learning for few-shot image classification. arXiv preprint arXiv:1811.11819 (2018)
Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521–3526 (2017)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)
Liu, V., Kumaraswamy, R., Le, L., White, M.: The utility of sparse representations for control in reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 4384–4391 (2019)
Lopez-Paz, D., Ranzato, M.: Gradient episodic memory for continual learning. arXiv preprint arXiv:1706.08840 (2017)
Nguyen, C.V., Li, Y., Bui, T.D., Turner, R.E.: Variational continual learning. arXiv preprint arXiv:1710.10628 (2017)
Qiao, S., Wang, H., Liu, C., Shen, W., Yuille, A.: Weight standardization. arXiv preprint arXiv:1903.10520 (2019)
Rao, D., Visin, F., Rusu, A.A., Teh, Y.W., Pascanu, R., Hadsell, R.: Continual unsupervised representation learning. arXiv preprint arXiv:1910.14481 (2019)
Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning (2016)
Riemer, M., et al.: Learning to learn without forgetting by maximizing transfer and minimizing interference. arXiv preprint arXiv:1810.11910 (2018)
Shin, H., Lee, J.K., Kim, J., Kim, J.: Continual learning with deep generative replay. arXiv preprint arXiv:1705.08690 (2017)
Smith, J., Baer, S., Taylor, C., Dovrolis, C.: Unsupervised progressive learning and the STAM architecture. arXiv preprint arXiv:1904.02021 (2019)
Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. arXiv preprint arXiv:1703.05175 (2017)
Van de Ven, G.M., Tolias, A.S.: Generative replay with feedback connections as a general strategy for continual learning. arXiv preprint arXiv:1809.10635 (2018)
Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. arXiv preprint arXiv:1606.04080 (2016)
Wu, Y., He, K.: Group normalization. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3–19 (2018)
Zenke, F., Poole, B., Ganguli, S.: Continual learning through synaptic intelligence. In: International Conference on Machine Learning, pp. 3987–3995. PMLR (2017)
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
Caccia, L., Pineau, J. (2022). SPeCiaL: Self-supervised Pretraining for Continual Learning. In: Cuzzolin, F., Cannons, K., Lomonaco, V. (eds) Continual Semi-Supervised Learning. CSSL 2021. Lecture Notes in Computer Science(), vol 13418. Springer, Cham. https://doi.org/10.1007/978-3-031-17587-9_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-17587-9_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-17586-2
Online ISBN: 978-3-031-17587-9
eBook Packages: Computer ScienceComputer Science (R0)