Skip to main content

Advertisement

SpringerLink
Log in

Continual meta-learning algorithm

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Deep learning has accomplished impressive excellence in many fields. However, its achievement relies on a vast amount of marker data and when there is insufficient labeled data, the phenomenon of over-fitting will occur. On the other hand, the real world tends to be so non-stationary that neural networks cannot learn continuously like humans. The specific manifestation is that learning new tasks leads to a significant decrease in its performance on old tasks. In responding to the above problem, this paper proposes a new algorithm CMLA (Continual Meta-Learning Algorithm) based on meta-learning. CMLA cannot only extract the key features of the sample, but also optimize the update method of the task gradient by introducing the cosine similarity judgment mechanism. The algorithm is tested on miniImageNet and Fewshot-CIFAR100 (Canadian Institute For Advanced Research), and the outcome clearly reveals the effectiveness and superiority of the CMLA in comparison with other advanced systems. Especially compared to MAML (Model-Agnostic Meta-Learning) with standard four-layer convolution, the accuracy of 1 shot and 5 shot is improved by 15.4% and 16.91% respectively under the setting of 5-way on miniImageNet. CMLA not only reduces the instability of the adaptation process, but also solves the stability-plasticity dilemma to a certain extent, achieving the goal of continual learning.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Availability of data and material

The datasets used during this study are available upon reasonable request to the authors.

Code availability

The code is publicly available at https://github.com/jiangmengjuan/CMLA

References

  1. Chen W Y, Liu Y C, Kira Z, Wang Y, Huang J (2019) A Closer Look at Few-shot Classification. In: 7Th international conference on learning representations. arxiv:1904.04232

  2. Gupta G, Yadav K, Paull L (2020) La-MAML: Look-ahead Meta Learning for Continual Learning. arXiv:2007.13904

  3. Javed K, White M (2019) Meta-Learning Representations for Continual Learning. In: Neural Information Processing Systems, pp 1818–1828

  4. Hadsell R, Rao D, Rusu A A, Pascanu R (2020) Embracing change: Continual learning in deep neural networks. Trends Cogn Sci:1028–1040

  5. Beaulieu S, Frati L, Miconi T, Lehman J, Stanley K, Clune J, Cheney N (2020) Learning to continually learn. In: 24Th european conference on artificial intelligence, vol 325, pp 992–1001. arxiv:2002.09571

  6. Finn C, Abbeel P, Levine S (2017) Model-Agnostic Meta-Learning For fast adaptation of deep networks. In: 34Th international conference on machine learning, pp. 70: 1126–1135. arxiv:1703.03400

  7. Kemker R, Kanan C (2018) Fearnet: Brain-inspired Model for Incremental Learning. In: 6Th international conference on learning representations. arxiv:1711.10563

  8. Parisi G I, Kemker R, Part J L, Kanan C, Wermter S (2018) Continual lifelong learning with neural networks: a review. Neural Netw 113:54–71. arXiv:1802.07569

    Article  Google Scholar 

  9. Kirkpatrick J, Pascanu R, Rabinowitz N, Veness J, Desjardins G, Rusu A A, Milan K, Quan J, Ramalho T, Grabska-Barwinska A, et al. (2016) Overcoming catastrophic forgetting in neural networks. Proc Natl Acad Sci 114(13):3521–3526

    Article  MathSciNet  Google Scholar 

  10. Soltoggio A (2015) Short-term plasticity as cause-effect hypothesis testing in distal reward learning. Biol Cybern 109(1):75–94

    Article  MathSciNet  Google Scholar 

  11. Rusu A A, Rabinowitz N C, Desjardins G, Soyer H, Kirkpatrick J, Kavukcuoglu K, Pascanu R, Hadsell R (2016) Progressive neural networks. arXiv:1606.04671

  12. Lu J, Gong P, Ye J, Zhang C (2020) Learning from Very Few Samples: A Survey. arXiv:2009.02653

  13. Snell J, Swersky K, Zemel R (2017) Prototypical Networks for Few-shot Learning. Neural Inf Process Syst:4077–4087

  14. Lee K, Maji S, Ravichandran A, Soatto S (2019) Meta-Learning With Differentiable Convex Optimization. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10649–10657

  15. Ye HJ, Hu H, Zhan DC, Sha F (2020) Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8805–8814

  16. Santoro A, Bartunov S, Botvinick M, Wierstra D, Lillicrap T (2016) Meta-learning with memory-augmented neural networks. Proc 33nd Int Conf Mach Learn 48:1842–1850

    Google Scholar 

  17. Al-Shedivat M, Bansal T, Burda Y, Sutskever I, Mordatch I, Abbeel P (2018) Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments. In: 6th International Conference on Learning Representations. arXiv:1710.03641

  18. Thung K H, Wee C Y (2018) A brief review on multi-task learning. Multimed Tools Appl 77 (22):29705–29725

    Article  Google Scholar 

  19. Caruana R (1997) Multi-task learning. Mach Learn 28(1):41–75

    Article  MathSciNet  Google Scholar 

  20. Ruder S (2017) An Overview of Multi-Task Learning in Deep Neural Networks. arXiv:1706.05098

  21. Zhang J, Ghahramani Z, Yang Y (2008) Flexible latent variable models for multi-task learning. Mach Learn 73(3):221–242

    Article  Google Scholar 

  22. Vandenhende S, Georgoulis S, Gansbeke W V, Proesmans M, Dai D, Gool L (2020) Multi-Task Learning for Dense Prediction Tasks: A Survey. arXiv:2004.13379

  23. Dong F, Liu L, Li F (2020) Multi-stage meta-learning for few-shot with lie group network constraint. Entropy 22(6):625

    Article  MathSciNet  Google Scholar 

  24. Lopez-Paz D, Ranzato M (2017) Gradient episodic memory for continual learning. Neural Inf Process Syst:6467–6476

  25. Hu J, Shen L, Sun G, Albanie S (2018) Squeeze-and-excitation networks. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7132–7141. arXiv:1709.01507

  26. Vinyals O, Blundell C, Lillicrap T, Kavukcuoglu K, Wierstra D (2016) Matching networks for one shot learning. Neural Inf Process Syst:3630–3638

  27. Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M S, Berg A, Li F F (2015) Imagenet Large Scale Visual Recognition Challenge. Int J Comput Vis 115(3):211–252

    Article  MathSciNet  Google Scholar 

  28. Krizhevsky A, Hinton G (2009) Learning multiple layers of features from tiny images. Handb Syst Autoimmune Diseas 1(4)

  29. Oreshkin B N, Lacoste A, Rodriguez P (2018) Tadam: task dependent adaptive metric for improved few-shot learning. Neural Inf Process Syst:719–729

  30. Bottou L (2010) Large-scale machine learning with stochastic gradient descent. In: 19th International Conference on Computational Statistics, pp. 177–186

  31. Kingma D, Ba J (2015) Adam: a method for stochastic optimization In: 3Rd international conference on learning representations. arxiv:1412.6980

  32. Sung F, Yang Y, Zhang L, Xiang T, Torr P, Hospedales TM (2018) Learning to Compare: Relation Network for Few-Shot Learning. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 1199–1208

  33. Zhang X, Qiang Y, Sung F, Yang Y, Hospedales TM (2018) Relationnet2: deep comparison columns for few-shot learning. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. arXiv:1811.07100v3

  34. Lifchitz Y, Avrithis Y, Picard S, Bursuc A (2019) Dense Classification and Implanting for Few-Shot Learning. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 9250–9259

  35. Ravichandran A, Bhotika R, Soatto S (2019) Few-Shot Learning With Embedded Class Models and Shot-Free Meta Training. 2019 IEEE/CVF International Conference on Computer Vision, pp 331–339

  36. Simon C, Koniusz P, Nock R, Harandi M (2020) Adaptive Subspaces for Few-Shot Learning. IEEE/CVF Conference on Computer Vision and Pattern Recognition

  37. Zhang RX, Che T, Grahahramani Z, Bengio Y, Song Y (2018) Metagan: An adversarial approach to few-shot learning. In: Neural Information Processing Systems, pp. 2371–2380

  38. Sun Q, Liu Y, Chua TS, Schiele B (2019) Meta-Transfer Learning for Few-Shot Learning. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 403–412

  39. Rusu A A, Rao D, Sygnowski J, Vinyals O, Pascanu R, Osindero S, Hadsell R (2019) Meta-Learning With latent embedding optimization. In: 7Th international conference on learning representations. arxiv:1807.05960

  40. Elsken T, Staffler B, Metzen JH, Hutter F (2020) Meta-Learning of Neural Architectures for Few-Shot Learning. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 12362–12372

  41. Guo Y, Cheung NM (2020) Attentive Weights Generation for Few Shot Learning via Information Maximization. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 13496–13505

  42. Ravi S, Larochelle H (2017) Optimization as a model for few shot learning. In: 5th International Conference on Learning Representations

  43. Li Z, Zhou F, Chen F, Li H (2017) Meta-SGD: Learning to Learn Quickly for Few Shot Learning. arXiv:1707.09835

  44. Mishra N, Rohaninejad M, Chen X, Abbeel P (2017) A simple neural attentive meta-learner. In: 6Th international conference on learning representations. arxiv:1707.03141

  45. Chen Y, Wang X, Liu Z, Xu H, Darrell T (2020) A new meta-baseline for few-shot learning. arXiv:2003.04390

  46. Ye H J, Sheng X R, Zhan D C (2020) Few-shot learning with adaptively initialized task optimizer: a practical meta-learning approach. Mach Learn 109(3):643–664

    Article  MathSciNet  Google Scholar 

  47. Zhang C, Cai Y, Lin G, Shen C (2020) Deepemd: differentiable earth mover’s distance for few-shot learning. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12200–12210

  48. Rajasegaran J, Khan S, Hayat M, Khan F, Shah M (2020) Self-supervised Knowledge Distillation for Few-shot Learning. arXiv:2006.09785

  49. Tian Y, Wang Y, Krishnan D, Tenenbaum J, Isola P (2020) Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?. ECCV 12359:266–282. arXiv:2003.11539

    Google Scholar 

  50. Afrasiyabi A, Lalonde J F, Gagné C (2020) Associative alignment for few-shot image classification. ECCV 12350:18–35

    Google Scholar 

  51. Liu Y, Schiele B, Sun Q (2020) An ensemble of Epoch-Wise empirical bayes for Few-Shot learning. ECCV 12361:404–421

    Google Scholar 

Download references

Acknowledgements

We would like to thank Fang Dong, Zhe Wang, Xiaohang Pan, Hui Dong, Yi Yi for their technical support. We would also like to thank the computer resources and other support provided by the Machine Learning Laboratory of Soochow University.

Funding

This work is supported by the National Key R&D Program of China (2018YFA0701700; 2018YFA0701701), and the National Natural Science Foundation of China under Grant No.61672364 and No.61902269.

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Soochow University, Suzhou, China

    Mengjuan Jiang, Fanzhang Li & Li Liu

Authors
  1. Mengjuan Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Fanzhang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Li Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors have contributed to the conception and design of the study. Conceptualization: Mengjuan Jiang, Fanzhang Li, and Li Liu; Experimentation: Mengjuan Jiang; Writing-original draft preparation: Mengjuan Jiang; Writing-review and editing: Mengjuan Jiang, Fanzhang Li, and Li Liu; Funding acquisition: Fanzhang Li; Supervision: Fanzhang Li and Li Liu. All authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Fanzhang Li.

Ethics declarations

Conflict of Interests

The authors declare no conflict of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jiang, M., Li, F. & Liu, L. Continual meta-learning algorithm. Appl Intell 52, 4527–4542 (2022). https://doi.org/10.1007/s10489-021-02543-8

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-021-02543-8

Keywords

Search

Navigation