Skip to main content
SpringerLink
Log in

Improving Self-supervised Dimensionality Reduction: Exploring Hyperparameters and Pseudo-Labeling Strategies

  • Conference paper
  • First Online:
Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1691))

  • 248 Accesses

Abstract

Dimensionality reduction (DR) is an essential tool for the visualization of high-dimensional data. The recently proposed Self-Supervised Network Projection (SSNP) method addresses DR with a number of attractive features, such as high computational scalability, genericity, stability and out-of-sample support, computation of an inverse mapping, and the ability of data clustering. Yet, SSNP has an involved computational pipeline using self-supervision based on labels produced by clustering methods and two separate deep learning networks with multiple hyperparameters. In this paper we explore the SSNP method in detail by studying its hyperparameter space and pseudo-labeling strategies. We show how these affect SSNP’s quality and how to set them to optimal values based on extensive evaluations involving multiple datasets, DR methods, and clustering algorithms.

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 69.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 89.99
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

References

  1. Amorim, E., Brazil, E.V., Daniels, J., Joia, P., Nonato, L.G., Sousa, M.C.: iLAMP: exploring high-dimensional spacing through backward multidimensional projection. In: Proceedings of IEEE VAST, pp. 53–62 (2012)

    Google Scholar 

  2. Anguita, D., Ghio, A., Oneto, L., Parra, X., Reyes-Ortiz, J.L.: Human activity recognition on smartphones using a multiclass hardware-friendly support vector machine. In: Bravo, J., Hervás, R., Rodríguez, M. (eds.) IWAAL 2012. LNCS, vol. 7657, pp. 216–223. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-35395-6_30

    Chapter  Google Scholar 

  3. Becker, M., Lippel, J., Stuhlsatz, A., Zielke, T.: Robust dimensionality reduction for data visualization with deep neural networks. Graph. Models 108, 101060 (2020)

    Article  Google Scholar 

  4. Chan, D., Rao, R., Huang, F., Canny, J.: T-SNE-CUDA: GPU-accelerated t-SNE and its applications to modern data. In: Proceedings of SBAC-PAD, pp. 330–338 (2018)

    Google Scholar 

  5. Cunningham, J., Ghahramani, Z.: Linear dimensionality reduction: survey, insights, and generalizations. JMLR 16, 2859–2900 (2015)

    MATH  Google Scholar 

  6. Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. J. Roy. Stat. Soc. Ser. B (Methodological) 39(1), 1–22 (1977)

    MATH  Google Scholar 

  7. Donoho, D.L., Grimes, C.: Hessian eigenmaps: locally linear embedding techniques for high-dimensional data. Proc. Natl. Acad. Sci. 100(10), 5591–5596 (2003)

    Article  MATH  Google Scholar 

  8. Engel, D., Hattenberger, L., Hamann, B.: A survey of dimension reduction methods for high-dimensional data analysis and visualization. In: Proceedings of IRTG Workshop, vol. 27, pp. 135–149. Schloss Dagstuhl (2012)

    Google Scholar 

  9. Espadoto, M., Falcao, A., Hirata, N., Telea, A.: Improving neural network-based multidimensional projections. In: Proceedings of IVAPP (2020)

    Google Scholar 

  10. Espadoto, M., Hirata, N., Telea, A.: Deep learning multidimensional projections. J. Inf. Vis. (2020). https://doi.org/10.1177/1473871620909485

  11. Espadoto, M., Hirata, N.S., Telea, A.C.: Self-supervised dimensionality reduction with neural networks and pseudo-labeling. In: Proceedings of IVAPP, pp. 27–37. SCITEPRESS (2021)

    Google Scholar 

  12. Espadoto, M., Martins, R.M., Kerren, A., Hirata, N.S., Telea, A.C.: Towards a quantitative survey of dimension reduction techniques. IEEE TVCG 27(3), 2153–2173 (2019)

    Google Scholar 

  13. Espadoto, M., Rodrigues, F.C.M., Hirata, N.S.T., Hirata Jr., R., Telea, A.C.: Deep learning inverse multidimensional projections. In: Proceedings of EuroVA, Eurographics (2019)

    Google Scholar 

  14. Ester, M., Kriegel, H.P., Sander, J., Xu, X., et al.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of KDD, vol. 96, pp. 226–231 (1996)

    Google Scholar 

  15. Fisher, R.A.: The use of multiple measurements in taxonomic problems. Ann. Eugenics 7(2), 179–188 (1936)

    Article  Google Scholar 

  16. Frey, B.J., Dueck, D.: Clustering by passing messages between data points. Science 315(5814), 972–976 (2007)

    Article  MATH  Google Scholar 

  17. Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of AISTATS, pp. 249–256 (2010)

    Google Scholar 

  18. He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of IEEE ICCV, pp. 1026–1034 (2015)

    Google Scholar 

  19. Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)

    Article  MATH  Google Scholar 

  20. Hoffman, P., Grinstein, G.: A survey of visualizations for high-dimensional data mining. Inf. Vis. Data Min. Knowl. Disc. 104, 47–82 (2002)

    Google Scholar 

  21. Joia, P., Coimbra, D., Cuminato, J.A., Paulovich, F.V., Nonato, L.G.: Local affine multidimensional projection. IEEE TVCG 17(12), 2563–2571 (2011)

    Google Scholar 

  22. Jolliffe, I.T.: Principal component analysis and factor analysis. In: Principal Component Analysis, pp. 115–128. Springer, New York (1986). https://doi.org/10.1007/978-1-4757-1904-8_7

  23. Kaufman, L., Rousseeuw, P.: Finding Groups in Data: An Introduction to Cluster Analysis. Wiley, Hoboken (2005)

    Google Scholar 

  24. Kehrer, J., Hauser, H.: Visualization and visual analysis of multifaceted scientific data: a survey. IEEE TVCG 19(3), 495–513 (2013)

    Google Scholar 

  25. Kingma, D.P., Welling, M.: Auto-encoding variational bayes. CoRR abs/1312.6114 (2013), eprint: 1312.6114

    Google Scholar 

  26. Kohonen, T.: Self-organizing Maps. Springer, Berlin (1997). https://doi.org/10.1007/978-3-642-97966-8

  27. Krogh, A., Hertz, J.A.: A simple weight decay can improve generalization. In: Proceedings of NIPS, pp. 950–957 (1992)

    Google Scholar 

  28. LeCun, Y., Cortes, C.: MNIST handwritten digits dataset (2010). http://yann.lecun.com/exdb/mnist

  29. Liu, S., Maljovec, D., Wang, B., Bremer, P.T., Pascucci, V.: Visualizing high-dimensional data: advances in the past decade. IEEE TVCG 23(3), 1249–1268 (2015)

    Google Scholar 

  30. Lloyd, S.: Least squares quantization in PCM. IEEE Trans Inf. Theor. 28(2), 129–137 (1982)

    Article  MATH  Google Scholar 

  31. Maaten, L.V.D.: Barnes-hut-SNE. arXiv preprint arXiv:1301.3342 (2013)

  32. Accelerating t-SNE using tree-based algorithms: Maaten, L.V.d. JMLR 15, 3221–3245 (2014)

    Google Scholar 

  33. Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. JMLR 9, 2579–2605 (2008)

    Google Scholar 

  34. Maaten, L.V.d., Postma, E.: Dimensionality reduction: a comparative review. Technical Report, Tilburg University, Netherlands (2009)

    Google Scholar 

  35. Martins, R.M., Minghim, R., Telea, A.C., et al.: Explaining neighborhood preservation for multidimensional projections. In: CGVC, pp. 7–14 (2015)

    Google Scholar 

  36. McInnes, L., Healy, J.: UMAP: uniform manifold approximation and projection for dimension reduction. arXiv:1802.03426v1 [stat.ML] (2018)

  37. Modrakowski, T.S., Espadoto, M., Falcão, A.X., Hirata, N.S.T., Telea, A.: Improving deep learning projections by neighborhood analysis. In: Bouatouch, K., et al. (eds.) VISIGRAPP 2020. CCIS, vol. 1474, pp. 127–152. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-94893-1_6

    Chapter  Google Scholar 

  38. Nonato, L., Aupetit, M.: Multidimensional projection for visual analytics: linking techniques with distortions, tasks, and layout enrichment. IEEE TVCG (2018). https://doi.org/10.1109/TVCG.2018.2846735

    Article  Google Scholar 

  39. Paulovich, F.V., Minghim, R.: Text map explorer: a tool to create and explore document maps. In: Proceedings of International Conference on Information Visualisation (IV), pp. 245–251. IEEE (2006)

    Google Scholar 

  40. Paulovich, F.V., Nonato, L.G., Minghim, R., Levkowitz, H.: Least square projection: a fast high-precision multidimensional projection technique and its application to document mapping. IEEE TVCG 14(3), 564–575 (2008)

    Google Scholar 

  41. Pedregosa, F., et al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. (JMLR) 12, 2825–2830 (2011)

    MATH  Google Scholar 

  42. Pezzotti, N., Höllt, T., Lelieveldt, B., Eisemann, E., Vilanova, A.: Hierarchical stochastic neighbor embedding. Comput. Graph. Forum 35(3), 21–30 (2016)

    Article  Google Scholar 

  43. Pezzotti, N., Lelieveldt, B., Maaten, L.V.d., Höllt, T., Eisemann, E., Vilanova, A.: Approximated and user steerable t-SNE for progressive visual analytics. IEEE TVCG 23, 1739–1752 (2017)

    Google Scholar 

  44. Pezzotti, N., et al.: GPGPU linear complexity t-SNE optimization. IEEE TVCG 26(1), 1172–1181 (2020)

    Google Scholar 

  45. Roweis, S.T., Saul, L.L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)

    Google Scholar 

  46. Salton, G., McGill, M.J.: Introduction to Modern Information Retrieval. McGraw-Hill, New York (1986)

    Google Scholar 

  47. Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE TPAMI 22(8), 888–905 (2000)

    Article  Google Scholar 

  48. Sorzano, C., Vargas, J., Pascual-Montano, A.: A survey of dimensionality reduction techniques (2014). arXiv:1403.2877 [stat.ML]

  49. Tenenbaum, J.B., Silva, V.D., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science 290(5500), 2319–2323 (2000)

    Article  Google Scholar 

  50. Thoma, M.: The Reuters dataset, July 2017. https://martin-thoma.com/nlp-reuters

  51. Torgerson, W.S.: Theory and Methods of Scaling. Wiley, Hoboken (1958)

    Google Scholar 

  52. Ulyanov, D.: Multicore-TSNE (2016). https://github.com/DmitryUlyanov/Multicore-TSNE

  53. Venna, J., Kaski, S.: Visualizing gene interaction graphs with local multidimensional scaling. In: Proceedings of ESANN, pp. 557–562 (2006)

    Google Scholar 

  54. Wattenberg, M.: How to use t-SNE effectively (2016). https://distill.pub/2016/misread-tsne

  55. Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms (2017). arXiv:1708.07747

  56. Xie, H., Li, J., Xue, H.: A survey of dimensionality reduction techniques based on random projection (2017). arXiv:1706.04371 [cs.LG]

  57. Zhang, Z., Wang, J.: MLLE: modified locally linear embedding using multiple weights. In: Advances in Neural Information Processing Systems (NIPS), pp. 1593–1600 (2007)

    Google Scholar 

  58. Zhang, Z., Zha, H.: Principal manifolds and nonlinear dimensionality reduction via tangent space alignment. SIAM J. Sci. Comput. 26(1), 313–338 (2004)

    Article  MATH  Google Scholar 

Download references

Acknowledgments

This study was financed in part by FAPESP grants 2015/22308-2, 2017/25835-9 and 2020/13275-1, and the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - Brasil (CAPES) - Finance Code 001.

Author information

Authors and Affiliations

  1. Institute of Mathematics and Statistics, University of São Paulo, São Paulo, Brazil

    Artur André A. M. Oliveira, Mateus Espadoto, Roberto Hirata Jr. & Nina S. T. Hirata

  2. Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands

    Alexandru C. Telea

Authors
  1. Artur André A. M. Oliveira
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mateus Espadoto
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Roberto Hirata Jr.
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Nina S. T. Hirata
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Alexandru C. Telea
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mateus Espadoto .

Editor information

Editors and Affiliations

  1. University of Porto, Porto, Portugal

    A. Augusto de Sousa

  2. Czech Technical University in Prague, Prague, Czech Republic

    Vlastimil Havran

  3. Mines ParisTech, Paris, France

    Alexis Paljic

  4. Davidson College, Davidson, NC, USA

    Tabitha Peck

  5. French Civil Aviation University (ENAC), Toulouse, France

    Christophe Hurter

  6. Monash University, Melbourne, Australia

    Helen Purchase

  7. University of Catania, Catania, Italy

    Giovanni Maria Farinella

  8. University of Barcelona, Barcelona, Spain

    Petia Radeva

  9. IRISA, University of Rennes 1, Rennes, France

    Kadi Bouatouch

Rights and permissions

Reprints and permissions

Copyright information

© 2023 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Oliveira, A.A.A.M., Espadoto, M., Hirata, R., Hirata, N.S.T., Telea, A.C. (2023). Improving Self-supervised Dimensionality Reduction: Exploring Hyperparameters and Pseudo-Labeling Strategies. In: de Sousa, A.A., et al. Computer Vision, Imaging and Computer Graphics Theory and Applications. VISIGRAPP 2021. Communications in Computer and Information Science, vol 1691. Springer, Cham. https://doi.org/10.1007/978-3-031-25477-2_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-25477-2_7

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-25476-5

  • Online ISBN: 978-3-031-25477-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation