Abstract
High-dimensional latent representations learned by neural network classifiers are notoriously hard to interpret. Especially in medical applications, model developers and domain experts desire a better understanding of how these latent representations relate to the resulting classification performance. We present Projective Latent Interventions (PLIs), a technique for retraining classifiers by back-propagating manual changes made to low-dimensional embeddings of the latent space. The back-propagation is based on parametric approximations of \(t\)-distributed stochastic neighbourhood embeddings. PLIs allow domain experts to control the latent decision space in an intuitive way in order to better match their expectations. For instance, the performance for specific pairs of classes can be enhanced by manually separating the class clusters in the embedding. We evaluate our technique on a real-world scenario in fetal ultrasound imaging.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The class cluster for class \(\gamma _j\) is simply the set of points \(\{y_i = E(C_l(x_i)) \mid g_i = \gamma _j\}\).
References
Baumgartner, C.F., et al.: SonoNet: real-time detection and localisation of fetal standard scan planes in freehand ultrasound. IEEE Trans. Med. Imaging 36(11), 2204–2215 (2017). https://doi.org/10.1109/TMI.2017.2712367
Bellet, A., Habrard, A., Sebban, M.: A survey on metric learning for feature vectors and structured data. arXiv preprint arXiv:1306.6709 (2013)
Brent, R.P.: Algorithms for minimization without derivatives. Courier Corporation (2013)
Chen, X., Weng, J., Lu, W., Xu, J., Weng, J.: Deep manifold learning combined with convolutional neural networks for action recognition. IEEE Trans. Neural Netw. Learn. Syst. 29(9), 3938–3952 (2017). https://doi.org/10.1109/TNNLS.2017.2740318
Dong, W., Moses, C., Li, K.: Efficient k-nearest neighbor graph construction for generic similarity measures. In: Proceedings of the 20th International Conference on World Wide Web, pp. 577–586 (2011). https://www.cs.princeton.edu/cass/papers/www11.pdf
Erhan, D., Bengio, Y., Courville, A., Manzagol, P.A., Vincent, P., Bengio, S.: Why does unsupervised pre-training help deep learning? J. Mach. Learn. Res. 11, 625–660 (2010). http://jmlr.org/papers/volume11/erhan10a/erhan10a.pdf
Krizhevsky, A., Nair, V., Hinton, G.: CIFAR-10 (Canadian Institute for Advanced Research). http://www.cs.toronto.edu/~kriz/cifar.html. Accessed 16 Mar 2020
Kulis, B., et al.: Metric learning: a survey. Found. Trends Mach. Learn. 5(4), 287–364 (2012)
LeCun, Y., Cortes, C.: The MNIST database of handwritten digits (2005). http://yann.lecun.com/exdb/mnist/. Accessed 16 Mar 2020
Lee, C.Y., Xie, S., Gallagher, P., Zhang, Z., Tu, Z.: Deeply-supervised nets. In: Artificial intelligence and statistics, pp. 562–570 (2015). https://www.proceedings.mlr.press/v38/lee15a.pdf
van der Maaten, L.: Learning a parametric embedding by preserving local structure. In: Artificial Intelligence and Statistics, pp. 384–391 (2009). http://proceedings.mlr.press/v5/maaten09a.html
van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008). https://lvdmaaten.github.io/publications/papers/JMLR_2008.pdf
McInnes, L., Healy, J., Melville, J.: UMAP: uniform manifold approximation and projection for dimension reduction, December 2018. arXiv:1802.03426
Mead, A.: Review of the development of multidimensional scaling methods. J. Roy. Stat. Soc. Ser. D (Stat.) 41(1), 27–39 (1992). https://doi.org/10.2307/2348634
Min, M.R., van der Maaten, L., Yuan, Z., Bonner, A.J., Zhang, Z.: Deep supervised t-distributed embedding. In: Proceedings of the 27th International Conference on Machine Learning (ICML 2010) (2010). https://www.cs.toronto.edu/~cuty/DSTEM.pdf
NHS: Fetal Anomaly Screening Programme: Programme Handbook June 2015. Public Health England (2015)
Poličar, P.G., Stražar, M., Zupan, B.: openTSNE: a modular Python library for t-SNE dimensionality reduction and embedding. bioRxiv, August 2019. https://doi.org/10.1101/731877. http://biorxiv.org/lookup/doi/10.1101/731877
Rauber, P.E., Fadel, S.G., Falcão, A.X., Telea, A.C.: Visualizing the hidden activity of artificial neural networks. IEEE Trans. Visual Comput. Graphics 23(1), 101–110 (2017)
Rusu, A.A., et al.: Meta-learning with latent embedding optimization (2018). arXiv:1807.05960
Tenenbaum, J.B.: Science, pp. 2319–2323. (2000). https://doi.org/10.1126/science.290.5500.2319. http://www.sciencemag.org/cgi/doi/10.1126/science.290.5500.2319
Tomar, V.S., Rose, R.C.: Manifold regularized deep neural networks. In: Fifteenth Annual Conference of the International Speech Communication Association (2014)
Wold, S., Esbensen, K., Geladi, P.: Principal component analysis. Chemometr. Intell. Lab. Syst. 2(1–3), 37–52 (1987). https://doi.org/10.1016/0169-7439(87)80084-9
Acknowledgments
This work was supported by the State of Upper Austria (Human-Interpretable Machine Learning) and the Austrian Federal Ministry of Education, Science and Research via the Linz Institute of Technology (LIT-2019-7-SEE-117), and by the Wellcome Trust (IEH 102431 and EPSRC EP/S013687/1.).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Hinterreiter, A., Streit, M., Kainz, B. (2020). Projective Latent Interventions for Understanding and Fine-Tuning Classifiers. In: Cardoso, J., et al. Interpretable and Annotation-Efficient Learning for Medical Image Computing. IMIMIC MIL3ID LABELS 2020 2020 2020. Lecture Notes in Computer Science(), vol 12446. Springer, Cham. https://doi.org/10.1007/978-3-030-61166-8_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-61166-8_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61165-1
Online ISBN: 978-3-030-61166-8
eBook Packages: Computer ScienceComputer Science (R0)
