Abstract
Explanatory Interactive Machine Learning queries user feedback regarding the prediction and the explanation of novel instances. CAIPI, a state-of-the-art algorithm, captures the user feedback and iteratively biases a data set toward a correct decision-making mechanism using counterexamples. The counterexample generation procedure relies on hand-crafted data augmentation and might produce implausible instances. We propose Bayesian CAIPI that embeds a Variational Autoencoder into CAIPI’s classification cycle and samples counterexamples from the likelihood distribution. Using the MNIST data set, where we distinguish ones from sevens, we show that Bayesian CAIPI matches the predictive accuracy of both, traditional CAIPI and default deep learning. Moreover, it outperforms both in terms of explanation quality.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Figure adapted from https://danijar.com/building-variational-auto-encoders-in-tensorflow/, 2023/07/11.
- 2.
Architecture adapted from https://www.tensorflow.org/tutorials/generative/cvae, 2023/07/11.
- 3.
http://yann.lecun.com/exdb/mnist/, 2023/07/11.
References
Amershi, S., Cakmak, M., Knox, W.B., Kulesza, T.: Power to the people: the role of humans in interactive machine learning. AI Mag. 35(4), 105–120 (2014). https://doi.org/10.1609/aimag.v35i4.2513
Blei, D.M., Kucukelbir, A., McAuliffe, J.D.: Variational inference: a review for statisticians. J. American Stat. Assoc. 112(518), 859–877 (Apr 2017). https://doi.org/10.1080/01621459.2017.1285773
Doersch, C.: Tutorial on variational autoencoders (2016). https://arxiv.org/abs/1606.05908
Ji, T., Vuppala, S.T., Chowdhary, G., Driggs-Campbell, K.R.: Multi-modal anomaly detection for unstructured and uncertain environments. In: Kober, J., Ramos, F., Tomlin, C.J. (eds.) 4th Conference on Robot Learning, CoRL 2020, 16–18 November 2020, Virtual Event / Cambridge, MA, USA. Proceedings of Machine Learning Research, vol. 155, pp. 1443–1455. PMLR (2020). https://proceedings.mlr.press/v155/ji21a.html
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7–9, 2015, Conference Track Proceedings (2015). https://arxiv.org/abs/1412.6980
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: Bengio, Y., LeCun, Y. (eds.) 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14–16, 2014, Conference Track Proceedings (2014). https://arxiv.org/abs/1312.6114
Kulesza, T., Burnett, M.M., Wong, W., Stumpf, S.: Principles of explanatory debugging to personalize interactive machine learning. In: Brdiczka, O., Chau, P., Carenini, G., Pan, S., Kristensson, P.O. (eds.) Proceedings of the 20th International Conference on Intelligent User Interfaces, IUI 2015, Atlanta, GA, USA, March 29 - April 01, 2015, pp. 126–137. ACM (2015). https://doi.org/10.1145/2678025.2701399
Nakao, Y., Stumpf, S., Ahmed, S., Naseer, A., Strappelli, L.: Toward involving end-users in interactive human-in-the-loop AI Fairness. ACM Trans. Interact. Intell. Syst. 12(3), 1–3 (Jul 2022). https://doi.org/10.1145/3514258
Pfeuffer, N., et al.: Explanatory interactive machine learning. Business Inform. Syst. Eng. (2023). https://doi.org/10.1007/s12599-023-00806-x
Pu, Y., et al.: Variational autoencoder for deep learning of images, labels and captions. In: Lee, D.D., Sugiyama, M., von Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5–10, 2016, Barcelona, Spain, pp. 2352–2360 (2016)
Ribeiro, M.T., Singh, S., Guestrin, C.: "Why should I trust you?": explaining the predictions of any classifier. In: Krishnapuram, B., Shah, M., Smola, A.J., Aggarwal, C.C., Shen, D., Rastogi, R. (eds.) Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, August 13–17, 2016, pp. 1135–1144. ACM (2016). https://doi.org/10.1145/2939672.2939778
Salimans, T., Kingma, D.P., Welling, M.: Markov chain monte carlo and variational inference: bridging the gap. In: Bach, F.R., Blei, D.M. (eds.) Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6–11 July 2015. JMLR Workshop and Conference Proceedings, vol. 37, pp. 1218–1226. JMLR.org (2015). https://ngs.mlr.press/v37/salimans15.html
Cellier, P., Driessens, K. (eds.): Machine Learning and Knowledge Discovery in Databases: International Workshops of ECML PKDD 2019, Würzburg, Germany, September 16–20, 2019, Proceedings, Part I. Springer International Publishing, Cham (2020)
Schramowski, P., et al.: Making deep neural networks right for the right scientific reasons by interacting with their explanations. Nature Mach. Intell. 2(8), 476–486 (2020). https://doi.org/10.1038/s42256-020-0212-3
Settles, B.: Active Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning, Morgan & Claypool Publishers (2012). https://doi.org/10.2200/S00429ED1V01Y201207AIM018
Shivaswamy, P., Joachims, T.: Coactive Learning. J. Artif. Intell. Res. 53, 1–40 (2015). https://doi.org/10.1613/jair.4539
Maglogiannis, I., Iliadis, L., Macintyre, J., Cortez, P. (eds.): Artificial Intelligence Applications and Innovations. AIAI 2022 IFIP WG 12.5 International Workshops: MHDW 2022, 5G-PINE 2022, AIBMG 2022, ML@HC 2022, and AIBEI 2022, Hersonissos, Crete, Greece, June 17–20, 2022, Proceedings. Springer International Publishing, Cham (2022)
Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6–11 August 2017. Proceedings of Machine Learning Research, vol. 70, pp. 3319–3328. PMLR (2017). http://proceedings.mlr.press/v70/sundararajan17a.html
Teso, S., Kersting, K.: Explanatory interactive machine learning. In: Conitzer, V., Hadfield, G.K., Vallor, S. (eds.) Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, AIES 2019, Honolulu, HI, USA, January 27–28, 2019, pp. 239–245. ACM (2019). https://doi.org/10.1145/3306618.3314293
Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.: Extracting and composing robust features with denoising autoencoders. In: Cohen, W.W., McCallum, A., Roweis, S.T. (eds.) Machine Learning, Proceedings of the Twenty-Fifth International Conference (ICML 2008), Helsinki, Finland, June 5–9, 2008. ACM International Conference Proceeding Series, vol. 307, pp. 1096–1103. ACM (2008). https://doi.org/10.1145/1390156.1390294
Ware, M., Frank, E., Holmes, G., Hall, M.A., Witten, I.H.: Interactive machine learning: letting users build classifiers. Int. J. Hum Comput Stud. 55(3), 281–292 (2001). https://doi.org/10.1006/ijhc.2001.0499
Shen, D., et al. (eds.): Medical Image Computing and Computer Assisted Intervention – MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part II. Springer International Publishing, Cham (2019)
Zhu, Q., Zhang, R.: A Classification Supervised Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids (2019). https://arxiv.org/abs/1902.00220
Acknowledgments
This research is funded by BMBF Germany (hKI-Chemie, # 01IS21023A).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Slany, E., Scheele, S., Schmid, U. (2024). Bayesian CAIPI: A Probabilistic Approach to Explanatory and Interactive Machine Learning. In: Nowaczyk, S., et al. Artificial Intelligence. ECAI 2023 International Workshops. ECAI 2023. Communications in Computer and Information Science, vol 1947. Springer, Cham. https://doi.org/10.1007/978-3-031-50396-2_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-50396-2_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-50395-5
Online ISBN: 978-3-031-50396-2
eBook Packages: Computer ScienceComputer Science (R0)