Techniques for interpretable machine learning

Abstract

Uncovering the mysterious ways machine learning models make decisions.

References

1. Altmann, A., Toloşi, L., Sander, O. and Lengauer T. Permutation importance: A corrected feature importance measure. Bioinformatics 26, 10 (2010), 1340--1347.
2. Ancona, M., Ceolini, E., Oztireli, C. and Gross, M. Towards better understanding of gradient-based attribution methods for deep neural networks. In Proceedings of the Intern. Conf. Learning Representations, 2018.
3. Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller K.-R. and Samek, W. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS One 10, 7 (2015), e0130140.
4. Bahdanau, D., Cho, K. and Bengio, Y. Neural machine translation by jointly learning to align and translate. In Proceedings of the Intern. Conf. Learning Representations, 2015.
5. Bastani, O., Kim, C., and Bastani, H. Interpretability via model extraction. In Proceedings of the Fairness, Accountability, and Transparency in Machine Learning Workshop, 2017.
6. Caruana, R., Lou, Y., Gehrke, J., Koch, P., Sturm, M. and Elhadad, N. Intelligible models for healthcare: Predicting pneumonia risk and hospital 30-day readmission. In Proceedings of the ACM SIGKDD Intern. Conf. Knowledge Discovery and Data Mining. ACM, 2015.
7. Chen, T. and Guestrin, C. Xgboost: A scalable tree boosting system. In Proceedings of the ACM SIGKDD Intern. Conf. Knowledge Discovery and Data Mining. ACM, 2016.
8. Dabkowski, P. and Gal, Y. Real time image saliency for black box classifiers. Advances in Neural Information Processing Systems (2017), 6970--6979.
9. Dix, A. Human issues in the use of pattern recognition techniques. Neural Networks and Pattern Recognition in Human Computer Interaction (1992), 429--451.
10. Doshi-Velez, F. and Kim, B. Towards a rigorous science of interpretable machine learning. 2017.
11. Du, M., Liu, N., Song, Q. and Hu, X. Towards explanation of DNN-based prediction with guided feature inversion. In Proceedings of the ACM SIGKDD Intern. Conf. Knowledge Discovery and Data Mining, 2018.
12. Du, M., Liu, N., Yang, F. and Hu, X. On attribution of recurrent neural network predictions via additive decomposition. In Proceedings of the WWW Conf., 2019.
13. Fong, R. and Vedaldi, A. Interpretable explanations of black boxes by meaningful perturbation. In Proceedings of the Intern. Conf. Computer Vision, 2017.
14. Freitas, A.A. Comprehensible classification models: A position paper. ACM SIGKDD Explorations Newsletter, 2014.
15. Goodfellow, I., Bengio, Y and Courville, A. Deep Learning, Vol.1. MIT Press, Cambridge, MA, 2016.
16. Goodfellow, I.J., Shlens, J. and Szegedy, C. Explaining and harnessing adversarial examples. In Proceedings of the Intern. Conf. Learning Representations, 2015.
17. Kádár, A., Chrupa-la, G., and Alishahi, A. Representation of linguistic form and function in recurrent neural networks. Computational Linguistics 43, 4 (2017), 761--780.
18. Karpathy, A., Johnson, J., and Fei-Fei, L. Visualizing and understanding recurrent networks. In Proceedings of the ICLR Workshop, 2016.
19. Liu, N., Du, M., and Hu, X. Representation interpretation with spatial encoding and multimodal analytics. In Proceedings of the ACM Intern. Conf. Web Search and Data Mining, 2019.
20. Liu, N., Yang, H., and Hu, X. Adversarial detection with model interpretation. In Proceedings of the ACM SIGKDD Intern. Conf. Knowledge Discovery and Data Mining, 2018.
21. McCullagh, P. and Nelder, J.A. Generalized Linear M, Vol. 37. CRC Press, 1989.
22. Miller, T. Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence (2018).
23. Molnar, C. Interpretable Machine Learning (2018); https://christophm.github.io/interpretable-ml-book/.
24. Mudrakarta, P.K., Taly, A., Sundararajan, M. and Dhamdhere, K. Did the model understand the question? In Proceedings of the 56^th Annual Meeting of the Assoc. Computational Linguistics, 2018.
25. Nguyen, A., Dosovitskiy, A., Yosinski, J., Brox, T. and Clune, J. Synthesizing the preferred inputs for neurons in neural networks via deep generator networks. Advances in Neural Information Processing Systems, 2016.
26. Nguyen, A., Yosinski, J. and Clune, J. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In Proceedings of the IEEE Conf. Computer Vision and Pattern Recognition, 2015.
27. Nguyen, A., Yosinski, J. and Clune, J. Multifaceted feature visualization: Uncovering the different types of features learned by each neuron in deep neural networks. In Proceedings of the ICLR Workshop, 2016.
28. Peters, M.E. et al. Deep contextualized word representations. In Proceedings of the NAACL-HLT, 2018.
29. Quinlan, J.R. Simplifying decision trees. Intern. J. Man-Machine Studies 27, 3 (1987), 221--234.
30. Ribeiro, M.T., Singh, S. and Guestrin, C. Why should I trust you? Explaining the predictions of any classifier. In Proceedings of the ACM SIGKDD Intern. Conf. Knowledge Discovery and Data Mining, 2016.
31. Ribeiro, M.T., Singh, S. and Guestrin, C. Anchors: High-precision model-agnostic explanations. In Proceedings of the AAAI Conf. Artificial Intelligence, 2018.
32. Sabour, S., Frosst, N. and Hinton, G.E. Dynamic routing between capsules. Advances in Neural Information Processing Systems, 2017.
33. Simonyan, K., Vedaldi, A. and Zisserman, A. Deep inside convolutional networks: Visualising image classification models and saliency maps. In Proceedings of the ICLR Workshop, 2014.
34. Springenberg, J.T., Dosovitskiy, A., Brox, T. and Riedmiller, M. Striving for simplicity: The all convolutional net. In Proceedings of the ICLR workshop, 2015.
35. Tomsett, R., Braines, D., Harborne, D., Preece, A. and Chakraborty, S. Interpretable to whom? A role-based model for analyzing interpretable machine learning systems. In Proceedings of the ICML Workshop on Human Interpretability in Machine Learning, 2018.
36. Vandewiele, G., Janssens, G., Ongenae, O., and Van Hoecke, F.S. Genesim: Genetic extraction of a single, interpretable model. In Proceedings of the NIPS Workshop, 2016.
37. Wachter, S., Mittelstadt, B. and Russell, C. Counterfactual explanations without opening the black box: Automated decisions and the GDPR. 2017.
38. Xu, K. et al. Show, attend and tell: Neural image caption generation with visual attention. In Proceedings of the Intern. Conf. Machine Learning, 2015.
39. Zhang, Q., Wu, Y.N. and Zhu, S.-C. Interpretable convolutional neural networks. In Proceedings of the IEEE Conf. Computer Vision and Pattern Recognition, 2018.
40. Zhou, B., Khosla, A., Lapedriza, A., Oliva, A. and Torralba, A. Object detectors emerge in deep scene CNNs. In Proceedings of the Intern. Conf. Learning Representations, 2015.

Index Terms

• Computing methodologies

  • Machine learning

    • Machine learning approaches