Abstract
While the concept of Explainability has advanced significantly in the past decade, many areas remain unexplored. Although XAI implementations have historically been employed in attempting to ‘open’ the traditional black-box model of supervised learning implementation aiming to extract human-understandable information, there are no successful attempts at tackling unsupervised learning. This paper aims to tackle the challenge of using an XAI approach, specifically Contextual Importance and Utility (CIU), in order to provide an explainability layer for unsupervised learning models. The paper introduces the current XAI approaches of CIU as well as the other state-of-the-art implementations such as Lime or Shapley. The challenges posed by the unsupervised learning problem are explored and discussed, both on a conceptual and technical level. A relatively novel approach using a CIU implementation on unsupervised clustering techniques is presented along with the brief comparison with another state-of-the-art method called LIME.
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
Similar content being viewed by others
Notes
- 1.
\(u_{j}(y_{j})\) could have any shape as long as it produces values in the range [0, 1] but that case goes beyond the scope of the current paper (and theory).
References
Crabbé, J., van der Schaar, M.: Label-free explainability for unsupervised models. arXiv preprint arXiv:2203.01928 (2022)
Främling, K.: Modélisation et apprentissage des préférences par réseaux de neurones pour l’aide à la décision multicritère. Ph.D. thesis, INSA de Lyon (1996)
Främling, K.: Contextual importance and utility in R: the ‘CIU’ package. In: Proceedings of 1st Workshop on Explainable Agency in Artificial Intelligence, at 35h AAAI Conference on Artificial Intelligence, 2–9 February 2021, pp. 110–114 (2021)
Främling, K., Graillot, D.: Extracting explanations from neural networks. In: Proceedings of the ICANN, vol. 95, pp. 163–168. Citeseer (1995)
Främling, K.: Contextual importance and utility in R: the ‘CIU’ package (2021)
Kannan, S., Ramathilagam, S., Chung, P.: Effective fuzzy C-means clustering algorithms for data clustering problems. Expert Syst. Appl. 39(7), 6292–6300 (2012). https://doi.org/10.1016/j.eswa.2011.11.063
Kauffmann, J., Esders, M., Ruff, L., Montavon, G., Samek, W., Müller, K.R.: From clustering to cluster explanations via neural networks. IEEE Trans. Neural Netw. Learn. Syst. (2022)
Knapič, S., Malhi, A., Saluja, R., Främling, K.: Explainable artificial intelligence for human decision support system in the medical domain. Mach. Learn. Knowl. Extract. 3(3), 740–770 (2021)
Lin, C., Chen, H., Kim, C., Lee, S.I.: Contrastive corpus attribution for explaining representations. arXiv preprint arXiv:2210.00107 (2022)
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 4765–4774. Curran Associates, Inc. (2017). http://papers.nips.cc/paper/7062-a-unified-approach-to-interpreting-model-predictions.pdf
Makarychev, K., Shan, L.: Near-optimal algorithms for explainable k-medians and k-means. In: International Conference on Machine Learning, pp. 7358–7367. PMLR (2021)
Malhi, A., Madhikermi, M., Huotari, M., Främling, K.: Air handling unit explainability using contextual importance and utility. In: Hara, T., Yamaguchi, H. (eds.) MobiQuitous 2021. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol. 419, pp. 513–519. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-94822-1_32
Miller, T.: Explanation in artificial intelligence: Insights from the social sciences. Artif. Intell. 267, 1–38 (2019). https://arxiv.org/abs/1706.07269
Moshkovitz, M., Dasgupta, S., Rashtchian, C., Frost, N.: Explainable k-means and k-medians clustering (2020). http://proceedings.mlr.press/v119/moshkovitz20a.html
Scholbeck, C.A., Funk, H., Casalicchio, G.: Algorithm-agnostic interpretations for clustering. arXiv preprint arXiv:2209.10578 (2022)
Unwin, A., Kleinman, K.: The iris data set: in search of the source of virginica. Significance 18, 26–29 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Malhi, A., Apopei, V., Främling, K. (2023). Understanding Unsupervised Learning Explanations Using Contextual Importance and Utility. In: Longo, L. (eds) Explainable Artificial Intelligence. xAI 2023. Communications in Computer and Information Science, vol 1901. Springer, Cham. https://doi.org/10.1007/978-3-031-44064-9_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-44064-9_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44063-2
Online ISBN: 978-3-031-44064-9
eBook Packages: Computer ScienceComputer Science (R0)