2000 character limit reached
Extracting Explanations, Justification, and Uncertainty from Black-Box Deep Neural Networks (2403.08652v1)
Published 13 Mar 2024 in cs.LG and stat.ML
Abstract: Deep Neural Networks (DNNs) do not inherently compute or exhibit empirically-justified task confidence. In mission critical applications, it is important to both understand associated DNN reasoning and its supporting evidence. In this paper, we propose a novel Bayesian approach to extract explanations, justifications, and uncertainty estimates from DNNs. Our approach is efficient both in terms of memory and computation, and can be applied to any black box DNN without any retraining, including applications to anomaly detection and out-of-distribution detection tasks. We validate our approach on the CIFAR-10 dataset, and show that it can significantly improve the interpretability and reliability of DNNs.
- Virani, N., Iyer, N., and Yang, Z., “Justification-based reliability in machine learning,” in [Proceedings of the AAAI Conference on Artificial Intelligence ], 34(04), 6078–6085 (2020).
- Snelson, E. and Ghahramani, Z., “Sparse Gaussian Processes using Pseudo-inputs,” in [Advances in Neural Information Processing Systems ], Weiss, Y., Schölkopf, B., and Platt, J., eds., 18, MIT Press (2006).
- Bui, T. D., Yan, J., and Turner, R. E., “A Unifying Framework for Gaussian Process Pseudo-Point Approximations Using Power Expectation Propagation,” Journal of Machine Learning Research 18(104), 1–72 (2017).
- Titsias, M., “Variational Learning of Inducing Variables in Sparse Gaussian Processes,” in [Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics ], van Dyk, D. and Welling, M., eds., 567–574, PMLR, Florida, USA (2009).
- Hoang, T. N., Hoang, Q. M., and Low, B. K. H., “A Unifying Framework of Anytime Sparse Gaussian Process Regression Models with Stochastic Variational Inference for Big Data,” in [Proceedings of the 32nd International Conference on Machine Learning ], Bach, F. and Blei, D., eds., 37, 569–578, PMLR, Lille, France (2015).
- Schwalbe, G. and Finzel, B., “A comprehensive taxonomy for explainable artificial intelligence: a systematic survey of surveys on methods and concepts,” Data Mining and Knowledge Discovery (2023).
- Neely, M., Schouten, S. F., Bleeker, M. J. R., and Lucic, A., “Order in the court: Explainable AI methods prone to disagreement,” CoRR abs/2105.03287 (2021).
- Suarez, J. L., Garcia, S., and Herrera, F., “Ordinal regression with explainable distance metric,” Machine Learning 110, 2729–2762 (2021).
- Quinonero-Candela, J., Rasmussen, C. E., and Williams, C. K. I., “Approximation Methods for Gaussian Process Regression,” in [Large-Scale Kernel Machines ], 203–223, MIT Press (2007).
- van der Wilk, M., Dutordoir, V., John, S., Artemev, A., Adam, V., and Hensman, J., “A Framework for Interdomain and Multioutput Gaussian Processes,” ArXiv (2020).
- Borovitskiy, V., Terenin, A., Mostowsky, P., and Deisenroth (he/him), M., “Matérn Gaussian processes on riemannian manifolds,” in [Advances in Neural Information Processing Systems ], Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., and Lin, H., eds., 33, 12426–12437, Curran Associates, Inc. (2020).
- Burt, D., Rasmussen, C. E., and Van Der Wilk, M., “Rates of Convergence for Sparse Variational Gaussian Process Regression,” in [Proceedings of the 36th International Conference on Machine Learning ], Chaudhuri, K. and Salakhutdinov, R., eds., 97, 862–871, PMLR (Jun 2019).
- Bauer, M., van der Wilk, M., and Rasmussen, C. E., “Understanding Probabilistic Sparse Gaussian Process Approximations,” in [Advances in Neural Information Processing Systems ], 1533–1541 (2016).
- Krizhevsky, A., “Learning multiple layers of features from tiny images,” (2009).