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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 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.
We use the implementations of [27], which are available at https://github.com/google-research/disentanglement_lib.
- 3.
Numerical values for reconstruction errors are presented in Appendix D.2 .
References
Abdi, A.H., Abolmaesumi, P., Fels, S.: Variational learning with disentanglement-pytorch. arXiv preprint arXiv:1912.05184 (2019)
Bedychaj, A., Spurek, P., Nowak, A., Tabor, J.: WICA: nonlinear weighted ICA (2020)
Bengio, Y.: Deep learning of representations: looking forward (2013)
Brakel, P., Bengio, Y.: Learning independent features with adversarial nets for non-linear ICA (2017)
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)
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)
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)
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)
Dinh, L., Krueger, D., Bengio, Y.: Nice: non-linear independent components estimation. arXiv preprint arXiv:1410.8516 (2014)
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
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)
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
Higgins, I., et al.: beta-VAE: Learning basic visual concepts with a constrained variational framework. In: ICLR (2017)
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)
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)
Huang, G.B., Wang, D.H., Lan, Y.: Extreme learning machines: a survey. Int. J. Mach. Learn. Cybernet. 2(2), 107–122 (2011)
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)
Hyvarinen, A., Morioka, H.: Nonlinear ICA of temporally dependent stationary sources. Proc. Mach. Learn. Res. (2017)
Kim, H., Mnih, A.: Disentangling by factorising. arXiv preprint arXiv:1802.05983 (2018)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)
Kumar, A., Sattigeri, P., Balakrishnan, A.: Variational inference of disentangled latent concepts from unlabeled observations. arXiv preprint arXiv:1711.00848 (2017)
Kumar, A., Sattigeri, P., Balakrishnan, A.: Variational inference of disentangled latent concepts from unlabeled observations (2018)
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)
Lipton, Z.C.: The mythos of model interpretability. Queue 16(3), 31–57 (2018)
Liu, X., He, P., Chen, W., Gao, J.: Multi-task deep neural networks for natural language understanding. arXiv preprint arXiv:1901.11504 (2019)
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)
Locatello, F., et al.: Challenging common assumptions in the unsupervised learning of disentangled representations (2019)
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)
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)
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)
McInnes, L., Healy, J., Melville, J.: UMAP: uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426 (2018)
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)
Petangoda, J.C., Pascual-Diaz, S., Adam, V., Vrancx, P., Grau-Moya, J.: Disentangled skill embeddings for reinforcement learning (2019)
Ruder, S.: An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098 (2017)
Sanchez, E.H., Serrurier, M., Ortner, M.: Learning disentangled representations via mutual information estimation (2019)
Schmidhuber, J.: Learning factorial codes by predictability minimization. Neural Comput. 4(6), 863–879 (1992)
Schölkopf, B., Janzing, D., Peters, J., Sgouritsa, E., Zhang, K., Mooij, J.: On causal and anticausal learning. arXiv preprint arXiv:1206.6471 (2012)
Sorrenson, P., Rother, C., Köthe, U.: Disentanglement by nonlinear ICA with general incompressible-flow networks (GIN) (2020)
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
Steenbrugge, X., Leroux, S., Verbelen, T., Dhoedt, B.: Improving generalization for abstract reasoning tasks using disentangled feature representations. arXiv preprint arXiv:1811.04784 (2018)
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)
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
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
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)