Skip to main content
SpringerLink
Log in

On the Relationship Between Disentanglement and Multi-task Learning

  • Conference paper
  • First Online:
Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2022)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 13713))

  • 937 Accesses

Abstract

One of the main arguments behind studying disentangled representations is the assumption that they can be easily reused in different tasks. At the same time finding a joint, adaptable representation of data is one of the key challenges in the multi-task learning setting. In this paper, we take a closer look at the relationship between disentanglement and multi-task learning based on hard parameter sharing. We perform a thorough empirical study of the representations obtained by neural networks trained on automatically generated supervised tasks. Using a set of standard metrics we show that disentanglement appears naturally during the process of multi-task neural network training.

Ł. Maziarka, A. Nowak, M. Worłczyk and A. Bedychaj—All authors contributed equally.

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 79.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 99.99
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.

    We provide the full model summary in Appendix A. The architecture of the encoder follows the one from [1], which adopts the work of [27] for the pytorch package. We use the implementations from https://github.com/amir-abdi/disentanglement-pytorch.

  2. 2.

    We use the implementations of [27], which are available at https://github.com/google-research/disentanglement_lib.

  3. 3.

    Numerical values for reconstruction errors are presented in Appendix D.2 .

References

  1. Abdi, A.H., Abolmaesumi, P., Fels, S.: Variational learning with disentanglement-pytorch. arXiv preprint arXiv:1912.05184 (2019)

  2. Bedychaj, A., Spurek, P., Nowak, A., Tabor, J.: WICA: nonlinear weighted ICA (2020)

    Google Scholar 

  3. Bengio, Y.: Deep learning of representations: looking forward (2013)

    Google Scholar 

  4. Brakel, P., Bengio, Y.: Learning independent features with adversarial nets for non-linear ICA (2017)

    Google Scholar 

  5. Capela, F., Nouchi, V., Van Deursen, R., Tetko, I.V., Godin, G.: Multitask learning on graph neural networks applied to molecular property predictions. arXiv preprint arXiv:1910.13124 (2019)

  6. Caruana, R.: Multitask learning: a knowledge-based source of inductive bias. In: Proceedings of the Tenth International Conference on Machine Learning, pp. 41–48. Morgan Kaufmann (1993)

    Google Scholar 

  7. Chen, R.T., Li, X., Grosse, R.B., Duvenaud, D.K.: Isolating sources of disentanglement in variational autoencoders. In: Advances in Neural Information Processing Systems, pp. 2610–2620 (2018)

    Google Scholar 

  8. Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. Adv. Neural. Inf. Process. Syst. 29, 2172–2180 (2016)

    Google Scholar 

  9. Dinh, L., Krueger, D., Bengio, Y.: Nice: non-linear independent components estimation. arXiv preprint arXiv:1410.8516 (2014)

  10. Do, K., Tran, T.: Theory and evaluation metrics for learning disentangled representations. In: International Conference on Learning Representations (2020). https://openreview.net/forum?id=HJgK0h4Ywr

  11. Duong, L., Cohn, T., Bird, S., Cook, P.: Low resource dependency parsing: Cross-lingual parameter sharing in a neural network parser. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pp. 845–850 (2015)

    Google Scholar 

  12. Eastwood, C., Williams, C.K.I.: A framework for the quantitative evaluation of disentangled representations. In: International Conference on Learning Representations (2018). https://openreview.net/forum?id=By-7dz-AZ

  13. Higgins, I., et al.: beta-VAE: Learning basic visual concepts with a constrained variational framework. In: ICLR (2017)

    Google Scholar 

  14. Hirayama, J., Hyvarinen, A., Kawanabe, M.: Splice: fully tractable hierarchical extension of ICA with pooling. In: Proceedings of the International Conference on Machine Learning, vol. 70, pp. 1491–1500. Machine Learning Research (2017)

    Google Scholar 

  15. Hsieh, J.T., Liu, B., Huang, D.A., Fei-Fei, L.F., Niebles, J.C.: Learning to decompose and disentangle representations for video prediction. In: Advances in Neural Information Processing Systems, pp. 517–526 (2018)

    Google Scholar 

  16. Huang, G.B., Wang, D.H., Lan, Y.: Extreme learning machines: a survey. Int. J. Mach. Learn. Cybernet. 2(2), 107–122 (2011)

    Article  Google Scholar 

  17. Hyvarinen, A., Morioka, H.: Unsupervised feature extraction by time-contrastive learning and nonlinear ICA. In: Advances in Neural Information Processing Systems, pp. 3765–3773 (2016)

    Google Scholar 

  18. Hyvarinen, A., Morioka, H.: Nonlinear ICA of temporally dependent stationary sources. Proc. Mach. Learn. Res. (2017)

    Google Scholar 

  19. Kim, H., Mnih, A.: Disentangling by factorising. arXiv preprint arXiv:1802.05983 (2018)

  20. Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)

  21. Kumar, A., Sattigeri, P., Balakrishnan, A.: Variational inference of disentangled latent concepts from unlabeled observations. arXiv preprint arXiv:1711.00848 (2017)

  22. Kumar, A., Sattigeri, P., Balakrishnan, A.: Variational inference of disentangled latent concepts from unlabeled observations (2018)

    Google Scholar 

  23. Lake, B.M., Ullman, T.D., Tenenbaum, J.B., Gershman, S.J.: Building machines that learn and think like people. Behav. Brain Sci. 40 (2017)

    Google Scholar 

  24. Lipton, Z.C.: The mythos of model interpretability. Queue 16(3), 31–57 (2018)

    Article  Google Scholar 

  25. Liu, X., He, P., Chen, W., Gao, J.: Multi-task deep neural networks for natural language understanding. arXiv preprint arXiv:1901.11504 (2019)

  26. Locatello, F., Abbati, G., Rainforth, T., Bauer, S., Schölkopf, B., Bachem, O.: On the fairness of disentangled representations. In: Advances in Neural Information Processing Systems, pp. 14611–14624 (2019)

    Google Scholar 

  27. Locatello, F., et al.: Challenging common assumptions in the unsupervised learning of disentangled representations (2019)

    Google Scholar 

  28. Locatello, F., Tschannen, M., Bauer, S., Rätsch, G., Schölkopf, B., Bachem, O.: Disentangling factors of variation using few labels. arXiv preprint arXiv:1905.01258 (2019)

  29. Ma, J., Zhou, C., Cui, P., Yang, H., Zhu, W.: Learning disentangled representations for recommendation. In: Advances in Neural Information Processing Systems, pp. 5711–5722 (2019)

    Google Scholar 

  30. Maziarka, Ł., Danel, T.: Multitask learning using BERT with task-embedded attention. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1–6. IEEE (2021)

    Google Scholar 

  31. McInnes, L., Healy, J., Melville, J.: UMAP: uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426 (2018)

  32. Misra, I., Shrivastava, A., Gupta, A., Hebert, M.: Cross-stitch networks for multi-task learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3994–4003 (2016)

    Google Scholar 

  33. Petangoda, J.C., Pascual-Diaz, S., Adam, V., Vrancx, P., Grau-Moya, J.: Disentangled skill embeddings for reinforcement learning (2019)

    Google Scholar 

  34. Ruder, S.: An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098 (2017)

  35. Sanchez, E.H., Serrurier, M., Ortner, M.: Learning disentangled representations via mutual information estimation (2019)

    Google Scholar 

  36. Schmidhuber, J.: Learning factorial codes by predictability minimization. Neural Comput. 4(6), 863–879 (1992)

    Article  MathSciNet  Google Scholar 

  37. Schölkopf, B., Janzing, D., Peters, J., Sgouritsa, E., Zhang, K., Mooij, J.: On causal and anticausal learning. arXiv preprint arXiv:1206.6471 (2012)

  38. Sorrenson, P., Rother, C., Köthe, U.: Disentanglement by nonlinear ICA with general incompressible-flow networks (GIN) (2020)

    Google Scholar 

  39. Spurek, P., Nowak, A., Tabor, J., Maziarka, Ł, Jastrzębski, S.: Non-linear ICA based on cramer-wold metric. In: Yang, H., Pasupa, K., Leung, A.C.-S., Kwok, J.T., Chan, J.H., King, I. (eds.) ICONIP 2020. LNCS, vol. 12534, pp. 294–305. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-63836-8_25

    Chapter  Google Scholar 

  40. Steenbrugge, X., Leroux, S., Verbelen, T., Dhoedt, B.: Improving generalization for abstract reasoning tasks using disentangled feature representations. arXiv preprint arXiv:1811.04784 (2018)

  41. Van Steenkiste, S., Locatello, F., Schmidhuber, J., Bachem, O.: Are disentangled representations helpful for abstract visual reasoning? In: Advances in Neural Information Processing Systems, pp. 14245–14258 (2019)

    Google Scholar 

Download references

Acknowledgements

The work of Ł. Maziarka was supported by the National Science Centre (Poland) grant no. 2019/35/N/ST6/02125. The work of A. Nowak and M. Wołczyk was supported by Foundation for Polish Science (grant no POIR 04.04.00-00-14DE/18-00) carried out within the Team-Net program co-financed by the European Union under the European Regional Development Fund.

Author information

Authors and Affiliations

  1. Jagiellonian University, Kraków, Poland

    Łukasz Maziarka, Aleksandra Nowak, Maciej Wołczyk & Andrzej Bedychaj

Authors
  1. Łukasz Maziarka
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Aleksandra Nowak
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Maciej Wołczyk
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Andrzej Bedychaj
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Łukasz Maziarka .

Editor information

Editors and Affiliations

  1. Grenoble Alpes University, Saint Martin d’Hères, France

    Massih-Reza Amini

  2. INSA Rouen Normandy, Saint Etienne du Rouvray, France

    Stéphane Canu

  3. Ruhr-Universität Bochum, Bochum, Germany

    Asja Fischer

  4. KU Leuven, Leuven, Belgium

    Tias Guns

  5. Central European University, Vienna, Austria

    Petra Kralj Novak

  6. Aristotle University of Thessaloniki, Thessaloniki, Greece

    Grigorios Tsoumakas

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 689 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Maziarka, Ł., Nowak, A., Wołczyk, M., Bedychaj, A. (2023). On the Relationship Between Disentanglement and Multi-task Learning. In: Amini, MR., Canu, S., Fischer, A., Guns, T., Kralj Novak, P., Tsoumakas, G. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2022. Lecture Notes in Computer Science(), vol 13713. Springer, Cham. https://doi.org/10.1007/978-3-031-26387-3_38

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-26387-3_38

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-26386-6

  • Online ISBN: 978-3-031-26387-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Societies and partnerships

Search

Navigation