Skip to main content

The Impact of Activation Sparsity on Overfitting in Convolutional Neural Networks

  • 1500 Accesses

Part of the Lecture Notes in Computer Science book series (LNIP,volume 12663)

Abstract

Overfitting is one of the fundamental challenges when training convolutional neural networks and is usually identified by a diverging training and test loss. The underlying dynamics of how the flow of activations induce overfitting is however poorly understood. In this study we introduce a perplexity-based sparsity definition to derive and visualise layer-wise activation measures. These novel explainable AI strategies reveal a surprising relationship between activation sparsity and overfitting, namely an increase in sparsity in the feature extraction layers shortly before the test loss starts rising. This tendency is preserved across network architectures and reguralisation strategies so that our measures can be used as a reliable indicator for overfitting while decoupling the network’s generalisation capabilities from its loss-based definition. Moreover, our differentiable sparsity formulation can be used to explicitly penalise the emergence of sparsity during training so that the impact of reduced sparsity on overfitting can be studied in real-time. Applying this penalty and analysing activation sparsity for well known regularisers and in common network architectures supports the hypothesis that reduced activation sparsity can effectively improve the generalisation and classification performance. In line with other recent work on this topic, our methods reveal novel insights into the contradicting concepts of activation sparsity and network capacity by demonstrating that dense activations can enable discriminative feature learning while efficiently exploiting the capacity of deep models without suffering from overfitting, even when trained excessively.

Keywords

  • Explainable AI
  • Sparstiy
  • Overfitting
  • Visualisation technique
  • CNNs

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-68796-0_10
  • Chapter length: 16 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   109.00
Price excludes VAT (USA)
  • ISBN: 978-3-030-68796-0
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   149.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.

References

  1. Ahmad, S., Scheinkman, L.: How can we be so dense? The benefits of using highly sparse representations. arXiv preprint arXiv:1903.11257 (2019)

  2. Ayinde, B.O., Inanc, T., Zurada, J.M.: On correlation of features extracted by deep neural networks. In: International Joint Conference on Neural Networks (IJCNN), Proceedings, pp. 1–8 (2019)

    Google Scholar 

  3. Ayinde, B.O., Inanc, T., Zurada, J.M.: Regularizing deep neural networks by enhancing diversity in feature extraction. IEEE Trans. Neural Netw. Learn. Syst. 30, 2650–2661 (2019)

    CrossRef  Google Scholar 

  4. Ayinde, B.O., Zurada, J.M.: Deep learning of constrained autoencoders for enhanced understanding of data. IEEE Trans. Neural Netw. Learn. Syst. 29(9), 3969–3979 (2017)

    CrossRef  Google Scholar 

  5. Bao, Y., Jiang, H., Dai, L., Liu, C.: Incoherent training of deep neural networks to de-correlate bottleneck features for speech recognition. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 6980–6984. IEEE (2013)

    Google Scholar 

  6. Bengio, Y., Bergstra, J.S.: Slow, decorrelated features for pretraining complex cell-like networks. In: Advances in Neural Information Processing Systems, pp. 99–107 (2009)

    Google Scholar 

  7. Changpinyo, S., Sandler, M., Zhmoginov, A.: The power of sparsity in convolutional neural networks. arXiv preprint arXiv:1702.06257 (2017)

  8. Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251–1258 (2017)

    Google Scholar 

  9. Cogswell, M., Ahmed, F., Girshick, R., Zitnick, L., Batra, D.: Reducing overfitting in deep networks by decorrelating representations. arXiv preprint arXiv:1511.06068 (2015)

  10. Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: AutoAugment: learning augmentation strategies from data. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Proceedings, pp. 113–123 (2019)

    Google Scholar 

  11. Frankle, J., Carbin, M.: The lottery ticket hypothesis: finding sparse, trainable neural networks. In: International Conference on Learning Representations (2018)

    Google Scholar 

  12. Gale, T., Elsen, E., Hooker, S.: The state of sparsity in deep neural networks. arXiv preprint arXiv:1902.09574 (2019)

  13. Gavrilov, A.D., Jordache, A., Vasdani, M., Deng, J.: Preventing model overfitting and underfitting in convolutional neural networks. Int. J. Softw. Sci. Comput. Intell. (IJSSCI) 10(4), 19–28 (2018)

    CrossRef  Google Scholar 

  14. Gomez, A.N., et al.: Learning sparse networks using targeted dropout. arXiv (2019)

    Google Scholar 

  15. Goodfellow, I.J., Bengio, Y., Courville, A.C.: Deep Learning. Adaptive Computation and Machine Learning. MIT Press, Cambridge (2016)

    MATH  Google Scholar 

  16. Guo, H., Mao, Y., Zhang, R.: Mixup as locally linear out-of-manifold regularization. In: AAAI Conference on Artificial Intelligence (AAAI), Proceedings, pp. 3714–3722 (2019)

    Google Scholar 

  17. Guo, Y., Zhang, C., Zhang, C., Chen, Y.: Sparse DNNs with improved adversarial robustness. In: Advances in Neural Information Processing Systems, pp. 242–251 (2018)

    Google Scholar 

  18. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  19. Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (ICML), Proceedings, pp. 448–456 (2015)

    Google Scholar 

  20. Khan, A., Sohail, A., Zahoora, U., Qureshi, A.S.: A survey of the recent architectures of deep convolutional neural networks. Artif. Intell. Rev. 53(8), 5455–5516 (2020). https://doi.org/10.1007/s10462-020-09825-6

    CrossRef  Google Scholar 

  21. Klemm, S., Ortkemper, R.D., Jiang, X.: Deploying deep learning into practice: a case study on fundus segmentation. In: Zheng, Y., Williams, B.M., Chen, K. (eds.) MIUA 2019. CCIS, vol. 1065, pp. 411–422. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-39343-4_35

    CrossRef  Google Scholar 

  22. Li, M., Soltanolkotabi, M., Oymak, S.: Gradient descent with early stopping is provably robust to label noise for overparameterized neural networks. In: International Conference on Artificial Intelligence and Statistics, pp. 4313–4324. PMLR (2020)

    Google Scholar 

  23. Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., Zhang, C.: Learning efficient convolutional networks through network slimming. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2736–2744 (2017)

    Google Scholar 

  24. Liu, Z., Sun, M., Zhou, T., Huang, G., Darrell, T.: Rethinking the value of network pruning. In: International Conference on Learning Representations (2018)

    Google Scholar 

  25. Mehta, D., Kim, K.I., Theobalt, C.: On implicit filter level sparsity in convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 520–528 (2019)

    Google Scholar 

  26. Miller, D.J., Rao, A.V., Rose, K., Gersho, A.: A global optimization technique for statistical classifier design. IEEE Trans. Signal Process. 44(12), 3108–3122 (1996)

    CrossRef  Google Scholar 

  27. Molchanov, P., Tyree, S., Karras, T., Aila, T., Kautz, J.: Pruning convolutional neural networks for resource efficient inference. In: 5th International Conference on Learning Representations, ICLR 2017-Conference Track Proceedings (2019)

    Google Scholar 

  28. Nowlan, S.J., Hinton, G.E.: Simplifying neural networks by soft weight-sharing. Neural Comput. 4(4), 473–493 (1992)

    CrossRef  Google Scholar 

  29. Pereyra, G., Tucker, G., Chorowski, J., Kaiser, L., Hinton, G.E.: Regularizing neural networks by penalizing confident output distributions. In: International Conference on Learning Representations (ICLR), Proceedings (2017)

    Google Scholar 

  30. Prechelt, L.: Early stopping - but when? In: Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 1524, pp. 55–69. Springer, Heidelberg (1998). https://doi.org/10.1007/3-540-49430-8_3

    CrossRef  Google Scholar 

  31. Rhu, M., O’Connor, M., Chatterjee, N., Pool, J., Kwon, Y., Keckler, S.W.: Compressing DMA engine: leveraging activation sparsity for training deep neural networks. In: 2018 IEEE International Symposium on High Performance Computer Architecture (HPCA), pp. 78–91 (2018)

    Google Scholar 

  32. Seelig, J.D., et al.: Two-photon calcium imaging from head-fixed drosophila during optomotor walking behavior. Nat. Methods 7(7), 535 (2010)

    CrossRef  Google Scholar 

  33. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Computational and Biological Learning Society (2015)

    Google Scholar 

  34. Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. (JMLR) 15(1), 1929–1958 (2014)

    MathSciNet  MATH  Google Scholar 

  35. Tu, Z., et al.: A survey of variational and CNN-based optical flow techniques. Sig. Process. Image Commun. 72, 9–24 (2019)

    CrossRef  Google Scholar 

  36. Vinje, W.E., Gallant, J.L.: Sparse coding and decorrelation in primary visual cortex during natural vision. Science 287(5456), 1273–1276 (2000)

    CrossRef  Google Scholar 

  37. Werpachowski, R., György, A., Szepesvári, C.: Detecting overfitting via adversarial examples. In: Advances in Neural Information Processing Systems, pp. 7856–7866 (2019)

    Google Scholar 

  38. Yaguchi, A., Suzuki, T., Asano, W., Nitta, S., Sakata, Y., Tanizawa, A.: Adam induces implicit weight sparsity in rectifier neural networks. In: IEEE International Conference on Machine Learning and Applications (ICMLA), Proceedings, pp. 318–325 (2018)

    Google Scholar 

  39. Yang, Q., Mao, J., Wang, Z., Li, H.: DASNet: dynamic activation sparsity for neural network efficiency improvement. In: 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), pp. 1401–1405. IEEE (2019)

    Google Scholar 

  40. Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning requires rethinking generalization. In: International Conference on Learning Representations (ICLR), Proceedings (2017)

    Google Scholar 

  41. Zhang, C., Vinyals, O., Munos, R., Bengio, S.: A study on overfitting in deep reinforcement learning. arXiv preprint arXiv:1804.06893 (2018)

  42. Zhou, H., Lan, J., Liu, R., Yosinski, J.: Deconstructing lottery tickets: zeros, signs, and the supermask. In: Advances in Neural Information Processing Systems, pp. 3592–3602 (2019)

    Google Scholar 

Download references

Acknowledgements

BR would like to thank the Ministeriums für Kultur und Wissenschaft des Landes Nordrhein-Westfalen for the AI Starter support (ID 005-2010-005). Moreover, the authors would like to sincerely thank Sören Klemm for his valuable ideas and input throughout this project and the WWU IT for the usage of the PALMA2 supercomputer. This work was partially supported by the Deutsche Forschungsgemeinschaft (DFG) under contract LI 1530/21-2.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Benjamin Risse .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Huesmann, K., Rodriguez, L.G., Linsen, L., Risse, B. (2021). The Impact of Activation Sparsity on Overfitting in Convolutional Neural Networks. In: , et al. Pattern Recognition. ICPR International Workshops and Challenges. ICPR 2021. Lecture Notes in Computer Science(), vol 12663. Springer, Cham. https://doi.org/10.1007/978-3-030-68796-0_10

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-68796-0_10

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-68795-3

  • Online ISBN: 978-3-030-68796-0

  • eBook Packages: Computer ScienceComputer Science (R0)