Abstract
In recent years, Artificial Intelligence (AI) algorithms have been proven to outperform traditional statistical methods in terms of predictivity, especially when a large amount of data was available. Nevertheless, the “black box” nature of AI models is often a limit for a reliable application in high-stakes fields like diagnostic techniques, autonomous guide, etc. Recent works have shown that an adequate level of interpretability could enforce the more general concept of model trustworthiness [7]. The basic idea of this paper is to exploit the human prior knowledge of the features’ importance for a specific task, in order to coherently aid the phase of the model’s fitting. This sort of “weighted” AI is obtained by extending the empirical loss with a regularization term encouraging the importance of the features to follow predetermined constraints. This procedure relies on local methods for the feature importance computation, e.g. LRP, LIME, etc. that are the link between the model weights to be optimized and the user-defined constraints on feature importance. In the fairness area, promising experimental results have been obtained for the Adult dataset. Many other possible applications of this model agnostic theoretical framework are described.
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.
With regularization chosen to be 0.1 and constraining also the other features, by using regularization strengths given by \(\lambda \cdot \rho _{\text {gender}, i}\) (see Eq. (5)).
- 2.
In linear regression a similar problem is called attenuation bias, where errors in the input features cause the weights going toward zero.
References
Al Iqbal, R.: Empirical learning aided by weak domain knowledge in the form of feature importance. In: 2011 International Conference on Multimedia and Signal Processing, vol. 1, pp. 126–130. IEEE (2011)
Arrieta, A.B., et al.: Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 58, 82–115 (2020)
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.R., Samek, W.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS One 10(7), e0130140 (2015)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001). https://doi.org/10.1023/a:1010933404324
Calders, T., Žliobaitė, I.: Why unbiased computational processes can lead to discriminative decision procedures. In: Custers, B., Calders, T., Schermer, B., Zarsky, T. (eds.) Discrimination and Privacy in the Information Society, pp. 43–57. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-30487-3_3
Diersen, S., Lee, E.J., Spears, D., Chen, P., Wang, L.: Classification of seismic windows using artificial neural networks. Procedia Comput. Sci. 4, 1572–1581 (2011)
Doshi-Velez, F., Kim, B.: Towards a rigorous science of interpretable machine learning. arXiv preprint. arXiv:1702.08608 (2017)
Dua, D., Graff, C.: UCI machine learning repository (2017). http://archive.ics.uci.edu/ml
Grgic-Hlaca, N., Zafar, M.B., Gummadi, K.P., Weller, A.: The case for process fairness in learning: feature selection for fair decision making. In: NIPS Symposium on Machine Learning and the Law, vol. 1, p. 2 (2016)
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. (CSUR) 51(5), 1–42 (2018)
Hardt, M., Price, E., Srebro, N.: Equality of opportunity in supervised learning. Adv. Neural Inf. Process. Syst. 29, 3315–3323 (2016)
Iqbal, R.A.: Using feature weights to improve performance of neural networks. arXiv preprint. arXiv:1101.4918 (2011)
Kamiran, F., Calders, T.: Data preprocessing techniques for classification without discrimination. Knowl. Inf. Syst. 33(1), 1–33 (2012). https://doi.org/10.1007/s10115-011-0463-8
Kamishima, T., Akaho, S., Sakuma, J.: Fairness-aware learning through regularization approach. In: 2011 IEEE 11th International Conference on Data Mining Workshops, pp. 643–650. IEEE (2011)
Kusner, M.J., Loftus, J.R., Russell, C., Silva, R.: Counterfactual fairness. arXiv preprint. arXiv:1703.06856 (2017)
Lipton, Z.C.: The mythos of model interpretability: In machine learning, the concept of interpretability is both important and slippery. Queue 16(3), 31–57 (2018)
Lou, Y., Caruana, R., Gehrke, J.: Intelligible models for classification and regression. In: Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 150–158 (2012)
Lou, Y., Caruana, R., Gehrke, J., Hooker, G.: Accurate intelligible models with pairwise interactions. In: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 623–631 (2013)
Lundberg, S., Lee, S.I.: A unified approach to interpreting model predictions. arXiv preprint. arXiv:1705.07874 (2017)
Montavon, G., Samek, W., Müller, K.R.: Methods for interpreting and understanding deep neural networks. Digital Signal Process. 73, 1–15 (2018)
Peng, X., Zhu, Y.: A novel feature weighted strategy on data classification. In: 2018 IEEE 3rd International Conference on Cloud Computing and Internet of Things (CCIOT), pp. 589–594. IEEE (2018)
Recknagel, F., French, M., Harkonen, P., Yabunaka, K.I.: Artificial neural network approach for modelling and prediction of algal blooms. Ecol. Model. 96(1–3), 11–28 (1997)
Ribeiro, M.T., Singh, S., Guestrin, C.: “why should i trust you?" explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144 (2016)
Shrikumar, A., Greenside, P., Kundaje, A.: Learning important features through propagating activation differences. In: International Conference on Machine Learning, pp. 3145–3153. PMLR (2017)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint. arXiv:1312.6034 (2013)
Strumbelj, E., Kononenko, I.: An efficient explanation of individual classifications using game theory. J. Mach. Learn. Res. 11, 1–18 (2010)
Štrumbelj, E., Kononenko, I.: Explaining prediction models and individual predictions with feature contributions. Knowl. Inf. Syst. 41(3), 647–665 (2013). https://doi.org/10.1007/s10115-013-0679-x
Sundararajan, M., Taly, A., Yan, Q.: Gradients of counterfactuals. arXiv preprint. arXiv:1611.02639 (2016)
Zhang, L., Wang, Z.: Ontology-based clustering algorithm with feature weights. J. Comput. Inf. Syst. 6(9), 2959–2966 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Picchiotti, N., Gori, M. (2022). Logic Constraints to Feature Importance. In: Bandini, S., Gasparini, F., Mascardi, V., Palmonari, M., Vizzari, G. (eds) AIxIA 2021 – Advances in Artificial Intelligence. AIxIA 2021. Lecture Notes in Computer Science(), vol 13196. Springer, Cham. https://doi.org/10.1007/978-3-031-08421-8_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-08421-8_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08420-1
Online ISBN: 978-3-031-08421-8
eBook Packages: Computer ScienceComputer Science (R0)