Abstract
From a dataset, one can construct different machine learning (ML) models with different parameters and/or inductive biases. Although these models give similar prediction performances when tested on data that are currently available, they may not generalise equally well on unseen data. The existence of multiple equally performing models exhibits underspecification of the ML pipeline used for producing such models. In this work, we propose identifying underspecification using feature attribution algorithms developed in Explainable AI. Our hypothesis is: by studying the range of explanations produced by ML models, one can identify underspecification. We validate this by computing explanations using the Shapley additive explainer and then measuring statistical correlations between them. We experiment our approach on multiple datasets drawn from the literature, and in a COVID-19 virus transmission case study.
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.
- 2.
- 3.
As can be seen from Eq. 4, when \(c_x\) is small, \(R_t\) can flatulate in a unrealistically large range and generate noises in the dataset.
References
Buolamwini, J., Gebru, T.: Gender shades: intersectional accuracy disparities in commercial gender classification. In: Friedler, S.A., Wilson, C. (eds.) FAT. Proceedings of Machine Learning Research, vol. 81, pp. 77–91. PMLR (2018)
bibitemch24chaudhari2019entropy Chaudhari, P., et al.: Entropy-SGD: biasing gradient descent into wide valleys. J. Stat. Mech: Theory Exp. 2019(12), 124018 (2019)
Cock, D.D.: Ames, iowa: Alternative to the Boston housing data as an end of semester regression project. J. Stat. Educ. 19(3) (2011)
D’Amour, A., et al.: Underspecification presents challenges for credibility in modern machine learning. CoRR abs/2011.03395 (2020)
Dua, D., Graff, C.: UCI machine learning repository (2017). http://archive.ics.uci.edu/ml
Fisher, A., Rudin, C., Dominici, F.: All models are wrong, but many are useful: Learning a variable’s importance by studying an entire class of prediction models simultaneously. J. Mach. Learn. Res. 20(177), 1–81 (2019)
Flaxman, S., et al.: Report 13: estimating the number of infections and the impact of non-pharmaceutical interventions on covid-19 in 11 European countries. Technical report, Imperial College London (2020)
Fort, S., Hu, H., Lakshminarayanan, B.: Deep ensembles: a loss landscape perspective. arXiv preprint arXiv:1912.02757 (2019)
Frankle, J., Dziugaite, G.K., Roy, D., Carbin, M.: Linear mode connectivity and the lottery ticket hypothesis. In: International Conference on Machine Learning, pp. 3259–3269. PMLR (2020)
Garg, S., Perot, V., Limtiaco, N., Taly, A., Chi, E.H., Beutel, A.: Counterfactual fairness in text classification through robustness. 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, 27–28 January 2019, pp. 219–226. ACM (2019)
Hendrycks, D., Dietterich, T.G.: Benchmarking neural network robustness to common corruptions and perturbations. CoRR abs/1903.12261 (2019)
Honegger, M.: Shedding light on black box machine learning algorithms: Development of an axiomatic framework to assess the quality of methods that explain individual predictions. CoRR abs/1808.05054 (2018)
Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., Wilson, A.G.: Averaging weights leads to wider optima and better generalization. arXiv preprint arXiv:1803.05407 (2018)
Lundberg, S.M., Lee, S.: A unified approach to interpreting model predictions. In: Guyon, I., von Luxburg, U., Bengio, S., Wallach, H.M., Fergus, R., Vishwanathan, S.V.N., Garnett, R. (eds.) Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4–9 December 2017, pp. 4765–4774. Long Beach, CA, USA (2017)
Marx, C., Calmon, F., Ustun, B.: Predictive multiplicity in classification. In: International Conference on Machine Learning, pp. 6765–6774. PMLR (2020)
McCoy, T., Pavlick, E., Linzen, T.: Right for the wrong reasons: diagnosing syntactic heuristics in natural language inference. In: Korhonen, A., Traum, D.R., Màrquez, L. (eds.) Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, pp. 3428–3448. Association for Computational Linguistics (2019)
Mei, S., Montanari, A.: The generalization error of random features regression: Precise asymptotics and double descent curve. arXiv preprint arXiv:1908.05355 (2019)
Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1–38 (2019)
Molnar, C.: Interpretable Machine Learning (2019). https://christophm.github.io/interpretable-ml-book/
Nakkiran, P., Kaplun, G., Bansal, Y., Yang, T., Barak, B., Sutskever, I.: Deep double descent: Where bigger models and more data hurt. arXiv preprint arXiv:1912.02292 (2019)
Obermeyer, Z., Powers, B., Vogeli, C., Mullainathan, S.: Dissecting racial bias in an algorithm used to manage the health of populations. Science 366(6464), 447–453 (2019)
Rathi, S.: Generating counterfactual and contrastive explanations using SHAP. CoRR abs/1906.09293 (2019)
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, San Francisco, CA, USA, 13–17 August 2016, pp. 1135–1144. ACM (2016)
Ribeiro, M.T., Wu, T., Guestrin, C., Singh, S.: Beyond accuracy: Behavioral testing of NLP models with checklist. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J.R. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, 5–10 July 2020, pp. 4902–4912. Association for Computational Linguistics (2020)
Ross, A.S., Hughes, M.C., Doshi-Velez, F.: Right for the right reasons: training differentiable models by constraining their explanations. In: Sierra, C. (ed.) Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI 2017, Melbourne, Australia, 19–25 August 2017, pp. 2662–2670. ijcai.org (2017)
Semenova, L., Rudin, C., Parr, R.: A study in rashomon curves and volumes: a new perspective on generalization and model simplicity in machine learning. arXiv preprint arXiv:1908.01755 (2019)
Slack, D., Hilgard, S., Jia, E., Singh, S., Lakkaraju, H.: Fooling LIME and SHAP: adversarial attacks on post hoc explanation methods. In: Markham, A.N., Powles, J., Walsh, T., Washington, A.L. (eds.) Proceedings of AIES, pp. 180–186. ACM (2020)
Wang, H., Ge, S., Lipton, Z.C., Xing, E.P.: Learning robust global representations by penalizing local predictive power. In: Wallach, H.M., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E.B., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8–14 December 2019, Vancouver, BC, Canada, pp. 10506–10518 (2019)
Wilson, A.G., Izmailov, P.: Bayesian deep learning and a probabilistic perspective of generalization. arXiv preprint arXiv:2002.08791 (2020)
Wu, J.T., et al.: Estimating clinical severity of covid-19 from the transmission dynamics in Wuhan, China. Nature Medicine, pp. 1–5 (2020)
Yalcin, O., Fan, X., Liu, S.: Evaluating the correctness of explainable AI algorithms for classification. CoRR abs/2105.09740 (2021)
Acknowledgements
This work is supported by the Welsh Government Office for Science, Ser Cymru III programme – Tackling Covid-19.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Hinns, J., Fan, X., Liu, S., Raghava Reddy Kovvuri, V., Yalcin, M.O., Roggenbach, M. (2021). An Initial Study of Machine Learning Underspecification Using Feature Attribution Explainable AI Algorithms: A COVID-19 Virus Transmission Case Study. In: Pham, D.N., Theeramunkong, T., Governatori, G., Liu, F. (eds) PRICAI 2021: Trends in Artificial Intelligence. PRICAI 2021. Lecture Notes in Computer Science(), vol 13031. Springer, Cham. https://doi.org/10.1007/978-3-030-89188-6_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-89188-6_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89187-9
Online ISBN: 978-3-030-89188-6
eBook Packages: Computer ScienceComputer Science (R0)