Skip to main content
SpringerLink
Log in

Autoencoder-Based Graph Construction for Semi-supervised Learning

  • Conference paper
  • First Online:
Computer Vision – ECCV 2020 (ECCV 2020)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 12369))

Included in the following conference series:

Abstract

We consider graph-based semi-supervised learning that leverages a similarity graph across data points to better exploit data structure exposed in unlabeled data. One challenge that arises in this problem context is that conventional matrix completion which can serve to construct a similarity graph entails heavy computational overhead, since it re-trains the graph independently whenever model parameters of an interested classifier are updated. In this paper, we propose a holistic approach that employs a parameterized neural-net-based autoencoder for matrix completion, thereby enabling simultaneous training between models of the classifier and matrix completion. We find that this approach not only speeds up training time (around a three-fold improvement over a prior approach), but also offers a higher prediction accuracy via a more accurate graph estimate. We demonstrate that our algorithm obtains state-of-the-art performances by respectful margins on benchmark datasets: Achieving the error rates of 0.57% on MNIST with 100 labels; 3.48% on SVHN with 1000 labels; and 6.87% on CIFAR-10 with 4000 labels.

M. Kang and K. Lee—Equal contribution.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    For GSCNN, we use the same CNN structure as in this paper, and incorporate a consistency loss for a fair comparison.

References

  1. Athiwaratkun, B., Finzi, M., Izmailov, P., Wilson, A.G.: There are many consistent explanations of unlabeled data: why you should average. In: Proceedings of the International Conference on Learning Representation (ICLR) (2019)

    Google Scholar 

  2. Belkin, M., Niyogi, P., Sindwani, V.: Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. J. Mach. Learn. Res. 7, 2399–2434 (2006)

    MathSciNet  MATH  Google Scholar 

  3. Berthelot, D., et al.: RemixMatch: semi-supervised learning with distribution alignment and augmentation anchoring. In: Proceedings of the International Conference on Representation Learning (ICLR) (2020)

    Google Scholar 

  4. Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A., Raffel, C.: MixMatch: a holistic approach to semi-supervised learning. In: Advances in Neural Information Processing Systems (NIPS), December 2019

    Google Scholar 

  5. Berton, L., Andrade Lopes, A.D.: Graph construction for semi-supervised learning. In: Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, pp. 4343–4344 (2015)

    Google Scholar 

  6. Blum, A., Chawla, S.: Learning from labeled and unlabeled data using graph mincuts. In: Proceedings of the International Conference on Machine Learning, pp. 19–26, June 2001

    Google Scholar 

  7. Bromley, J., Guyon, I., LeCun, Y., Sickinger, E., Shah, R.: Signature verification using a “Siamese” time delay neural network. In: Advances in Neural Information Processing Systems, pp. 737–744 (1994)

    Google Scholar 

  8. Candés, E.J., Recht, B.: Exact matrix completion via convex optimization. Found. Comput. Math. 9(6), 717–772 (2009)

    Article  MathSciNet  Google Scholar 

  9. Dai, X., Yang, Z., Yang, F., Cohen, W.W., Salakhutdinov, R.: Good semi-supervised learning that requires a bad GAN. In: Advances in Neural Information Processing Systems (NIPS), pp. 6510–6520, December 2017

    Google Scholar 

  10. Dong, X., Yu, L., Wu, Z., Sun, Y., Yuan, L., Zhang, F.: A hybrid collaborative filtering model with deep structure for recommender systems. In: Proceedings of the 31st AAAI Conference on Artificial Intelligence, pp. 1309–1315 (2017)

    Google Scholar 

  11. Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: International Conference on Artificial Intelligence and Statistics (2010)

    Google Scholar 

  12. Gong, C., Liu, T., Tao, D., Fu, K., Tu, E., Yang, J.: Deformed graph Laplacian for semisupervised learning. IEEE Trans. Neural Netw. Learn. Syst. 26(10), 717–772 (2015)

    Article  MathSciNet  Google Scholar 

  13. Goodfellow, I.J., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems (NIPS), December 2014

    Google Scholar 

  14. He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2015)

    Google Scholar 

  15. Iscen, A., Tolias, G., Avrithis, Y., Chum, O.: Label propagation for deep semi-supervised learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 5070–5079, June 2019

    Google Scholar 

  16. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: 3rd International Conference for Learning Representations (2015)

    Google Scholar 

  17. Kolesnikov, A., Zhai, X., Beyer, L.: Revisiting self-supervised visual representation learning. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)

    Google Scholar 

  18. Laine, S., Aila, T.: Temporal ensembling for semi-supervised learning. In: Proceedings of the International Conference on Representation Learning (ICLR), April 2017

    Google Scholar 

  19. Lee, D.H.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning, ICML, vol. 3, p. 2 (2013)

    Google Scholar 

  20. Lee, K., Jo, H., Kim, H., Lee, Y.H.: Basis learning autoencoders for hybrid collaborative filtering in cold start setting. In: Proceedings of the 29th International Workshop on Machine Learning for Signal Processing (MLSP) (2019)

    Google Scholar 

  21. Lee, K., Lee, Y.H., Suh, C.: Alternating autoencoders for matrix completion. In: Proceedings of the IEEE Data Science Workshop (DSW) (2018)

    Google Scholar 

  22. Li, C., Xu, K., Zhu, J., Zhang, B.: Triple generative adversarial nets. In: Advances in Neural Information Processing Systems (NIPS), pp. 4088–4098, December 2017

    Google Scholar 

  23. Li, S., Kawale, J., Fu, Y.: Deep collaborative filtering via marginalized denoising auto-encoder. In: Proceedings of the 24th ACM International Conference on Information and Knowledge Management, pp. 811–820. ACM (2015)

    Google Scholar 

  24. Luo, Y., Zhu, J., Li, M., Ren, Y., Zhang, B.: Smooth neighbors on teacher graphs for semi-supervised learning. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8896–8905, June 2018

    Google Scholar 

  25. Maaten, L., Hinton, G., Johnson, I.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)

    MATH  Google Scholar 

  26. Mazumder, R., Hastie, T., Tibshirani, R.: Spectral regularization algorithms for learning large incomplete matrices. J. Mach. Learn. Res. 11, 2287–2322 (2010)

    MathSciNet  MATH  Google Scholar 

  27. Miyato, T., Ichi Maeda, S., Koyama, M., Ishii, S.: Virtual adversarial training: a regularization method for supervised and semi-supervised learning. In: Proceedings of the International Conference on Representation Learning (ICLR), April 2017

    Google Scholar 

  28. Oliver, A., Odena, A., Raffel, C., Cubuk, E.D., Goodfellow, I.J.: Realistic evaluation of semi-supervised learning algorithms. In: Advances in Neural Information Processing Systems (NIPS), pp. 3235–3246, December 2018

    Google Scholar 

  29. Park, S., Park, J., Shin, S.J., Moon, I.C.: Adversarial dropout for supervised and semi-supervised learning. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, April 2018

    Google Scholar 

  30. Rasmus, A., Valpola, H., Honkala, M., Berglund, M., Raiko, T.: Semi-supervised learning with ladder networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 3546–3554, December 2015

    Google Scholar 

  31. Salimans, T., Kingma, D.: Weight normalization: a simple reparameterization to accelerate training of deep neural networks. In: Advances in Neural Information Processing Systems (NIPS) (2016)

    Google Scholar 

  32. Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems (NIPS), pp. 2234–2242, December 2016

    Google Scholar 

  33. Sedhain, S., Krishna, M., Scanner, S., Xie, L.: AutoRec: autoencoders meet collaborative filtering. In: Proceedings of the 24th International Conference on World Wide Web, pp. 111–112 (2015)

    Google Scholar 

  34. Sohn, K., et al.: Fixmatch: simplifying semi-supervised learning with consistency and confidence. arXiv preprint arXiv:2001.07685 (2020)

  35. Springenberg, J.T.: Unsupervised and semi-supervised learning with categorical generative adversarial networks. In: Proceedings of the International Conference on Learning Representation (ICLR), May 2016

    Google Scholar 

  36. Taherkhani, F., Kazemi, H., Nasrabadi, N.M.: Matrix completion for graph-based deep semi-supervised learning. In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence. pp. 8896–8905, January 2019

    Google Scholar 

  37. Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in Neural Information Processing Systems (NIPS), pp. 1195–1204, December 2017

    Google Scholar 

  38. Verma, V., Lamb, A., Kannala, J., Bengio, Y., Lopez-Paz, D.: Interpolation consistency training for semi-supervised learning. In: International Joint Conference on Artificial Intelligence, pp. 3635–3641, August 2019

    Google Scholar 

  39. Volkovs, M., Yu, G., Poutanen, T.: DropOutNet: addressing cold start in recommender systems. In: Advances in Neural Information Processing Systems (NIPS), December 2015

    Google Scholar 

  40. Wan, S., Gong, C., Zhong, P., Du, B., Zhang, L., Yang, J.: Multi-scale dynamic graph convolutional network for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 1–16 (2019)

    Google Scholar 

  41. Wang, B., Tu, Z., Tsotsos, J.K.: Dynamic label propagation for semi-supervised multi-class multi-label classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 425–432 (2013)

    Google Scholar 

  42. Wang, Q., Li, W., Gool, L.V.: Semi-supervised learning by augmented distribution alignment. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1466–1475 (2019)

    Google Scholar 

  43. Weston, J., Ratle, F., Collobert, R.: Deep learning via semi-supervised embedding. In: Proceedings of the 25th International Conference on Machine Learning, pp. 1168–1175, July 2008

    Google Scholar 

  44. Wu, S., Li, J., Liu, C., Yu, Z., Wong, H.S.: Mutual learning of complementary networks via residual correction for improving semi-supervised classification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6500–6509 (2019)

    Google Scholar 

  45. Wu, X., Zhao, L., Akoglu, L.: A quest for structure: jointly learning the graph structure and semi-supervised classification. In: In Proceedings of the 27th ACM International Conference on Information and Knowledge Management (2018)

    Google Scholar 

  46. Xie, Q., Dai, Z., Hovy, E., Luong, M.T., Le, Q.V.: Unsupervised data augmentation for consistency training. arXiv preprint arXiv:1904.12848 (2019)

  47. Zagoruyko, S., Komodakis, N.: Wide residual networks. In: Richard C. Wilson, E.R.H., Smith, W.A.P. (eds.) Proceedings of the British Machine Vision Conference (BMVC), pp. 87.1–87.12. BMVA Press, September 2016. https://doi.org/10.5244/C.30.87

  48. Zhai, X., Oliver, A., Kolesnikov, A., Beyer, L.: S4l: self-supervised semi-supervised learning. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), November 2019

    Google Scholar 

  49. Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. In: Proceedings of the International Conference on Learning Representation (2018)

    Google Scholar 

  50. Zhul, X., Ghahramani, Z.: Learning from labeled and unlabeled data with label propagation. Technical report (2002)

    Google Scholar 

  51. Ziang, B., Zhang, Z., Lin, D., Tang, J., Luo, B.: Semi-supervised learning with graph learning-convolutional networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)

    Google Scholar 

Download references

Acknowledgments

This work was supported by the ICT R&D program of MSIP/IITP (2016-0-00563, Research on Adaptive Machine Learning Technology Development for Intelligent Autonomous Digital Companion), and Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (2020-0-00626, Ensuring high AI learning performance with only a small amount of training data).

Author information

Authors and Affiliations

  1. KAIST, Daejeon, South Korea

    Mingeun Kang, Kiwon Lee & Changho Suh

  2. UNIST, Ulsan, South Korea

    Yong H. Lee

Authors
  1. Mingeun Kang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kiwon Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yong H. Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Changho Suh
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Changho Suh .

Editor information

Editors and Affiliations

  1. University of Oxford, Oxford, UK

    Andrea Vedaldi

  2. Graz University of Technology, Graz, Austria

    Horst Bischof

  3. University of Freiburg, Freiburg im Breisgau, Germany

    Thomas Brox

  4. University of North Carolina at Chapel Hill, Chapel Hill, NC, USA

    Jan-Michael Frahm

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 136 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Kang, M., Lee, K., Lee, Y.H., Suh, C. (2020). Autoencoder-Based Graph Construction for Semi-supervised Learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12369. Springer, Cham. https://doi.org/10.1007/978-3-030-58586-0_30

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-58586-0_30

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-58585-3

  • Online ISBN: 978-3-030-58586-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation