Understanding black-box predictions via influence functions

34th International Conference on Machine Learning, ICML 2017

Volumn 4, Issue , 2017, Pages 2976-2987

  Koh, Pang Wei ^a   Liang, Percy ^a  

^a STANFORD UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

FORECASTING; LEARNING SYSTEMS; METHOD OF MOMENTS; NEURAL NETWORKS;

CLASSIC TECHNIQUES; CONVOLUTIONAL NEURAL NETWORK; EFFICIENT IMPLEMENTATION; HESSIAN-VECTOR PRODUCTS; INFLUENCE FUNCTIONS; MODELING BEHAVIOR; NON-DIFFERENTIABLE; ROBUST STATISTICS;

LEARNING ALGORITHMS;

EID: 85048455773     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (49)

1. Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C, Corrado, G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I. J., Harp, A., Irving, G., Isard, M., Jia, Y., Józefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D. G., Olah, C, Schuster, M., Shlens, J., Steiner, B, Sutskever, I., Talwar, K., Tucker, P. A., Vanhoucke, V., Vasudevan, V., Viégas, F. B., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y, and Zheng, X. Ten-sorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv: 1603.04467, 2015.
2. Adler, P., Falk, C, Fricdler, S. A., Rybcck, G., Schcidcg-gcr, C, Smith, B., and Vcnkatasubramanian, S. Auditing black-box models for indirect influence. arXiv preprint arXiv: 1602.07043, 2016.
3. Agarwal, N., Bullins, B., and Hazan, E. Second order stochastic optimization in linear time. arXiv preprint arXiv: 1602.03943, 2016.
4. Amershi, S., Chickering, M., Drucker, S. M., Lee, B., Simard, P., and Suh, J. Modeltracker: Redesigning performance analysis tools for machine learning. In Conference on Human Factors in Computing Systems (CHI), pp. 337-346, 2015.
5. Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., and Vaughan, J. W. A theory of learning from different domains. Machine Learning, 79(1): 151-175, 2010.
6. Biggio, B., Nelson, B., and Laskov, P. Support vector machines under adversarial label noise. ACML, 20: 97-112, 2011.
7. Biggio, B., Nelson, B., and Laskov, P. Poisoning attacks against support vector machines. In International Conference on Machine Learning (ICML), pp. 1467-1474, 2012.
8. Cadamuro, G., Gilad-Bachrach, R., and Zhu, X. Debugging machine learning models. In ICML Workshop on Reliable Machine Learning in the Wild, 2016.
9. Chatterjee, S. and Hadi, A. S. Influential observations, high leverage points, and outliers in linear regression. Statistical Science, pp. 379-393, 1986.
10. Chollet, F. Keras, 2015.
11. Christmann, A. and Steinwart, I. On robustness properties of convex risk minimization methods for pattern recognition. Journal of Machine Learning Research (JMLR), 5(0): 1007-1034, 2004.
12. Cook, R. D. Detection of influential observation in linear regression. Technometrics, 19: 15-18, 1977.
13. Cook, R. D. Assessment of local influence. Journal of the Royal Statistical Society. Series B (Methodological), pp. 133-169, 1986.
14. Cook, R. D. and Weisberg, S. Characterizations of an empirical influence function for detecting influential cases in regression. Technometrics, 22: 495-508, 1980.
15. Cook, R. D. and Wcisbcrg, S. Residuals and influence in regression. New York: Chapman and Hall, 1982.
16. Datta, A., Sen, S., and Zick, Y. Algorithmic transparency via quantitative input influence: Theory and experiments with learning systems. In Security and Privacy (SP), 2016 IEEE Symposium on, pp. 598-617, 2016.
17. Debruyne, M., Hubert, M., and Suykens, J. A. Model selection in kernel based regression using the influence function. Journal of Machine Learning Research (JMLR), 9 (0): 2377-2400, 2008.
18. Donahue, J., Jia, Y, Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., and Darrell, T. Decaf: A deep convolutional activation feature for generic visual recognition. In International Conference on Machine Learning (ICML), volume 32, pp. 647-655, 2014.
19. Frénay, B. and Verleysen, M. Classification in the presence of label noise: a survey. IEEE Transactions on Neural Networks and teaming Systems, 25: 845-869, 2014.
20. Goodfellow, I. J., Shlens, J., and Szegedy, C. Explaining and harnessing adversarial examples. In International Conference on Learning Representations (ICLR), 2015.
21. Goodman, B. and Flaxman, S. European union regulations on algorithmic decision-making and a "right to explanation". arXiv preprint arXiv: 1606.08813, 2016.
22. Huang, L., Joseph, A. D., Nelson, B., Rubinstein, B. I., and Tygar, J. Adversarial machine learning. In Proceedings of the 4th ACM workshop on Security and artificial intelligence, pp. 43-58, 2011.
23. Jaeckel, L. A. The infinitesimal jackknife. Unpublished memorandum, Bell Telephone laboratories, Murray Hill, NJ, 1972.
24. Kansagara, D., Englander, H., Salanitro, A., Kagen, D., Theobald, C, Freeman, M., and Kripalani, S. Risk prediction models for hospital readmission: a systematic review. JAMA, 306(15): 1688-1698, 2011.
25. Kingma, D. and Ba, J. Adam: A method for stochastic optimization. arXiv preprint arXiv: 1412.6980, 2014.
26. Krizhevsky, A., Sutskever, I., and Hinton, G. E. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems (NIPS), pp. 1097-1105, 2012.
27. LeCun, Y, Bottou, L., Bengio, Y., and Haffner, P. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11): 2278-2324, 1998.
28. Li, B., Wang, Y, Singh, A., and Vorobeychik, Y. Data poisoning attacks on factorization-based collaborative filtering. In Advances in Neural Information Processing Systems (NIPS), 2016a.
29. Li, J., Monroe, W., and Jurafsky, D. Understanding neural networks through representation erasure. arXiv preprint arXiv: 1612.08220, 2016b.
30. Liu, D. C. and Nocedal, J. On the limited memory BFGS method for large scale optimization. Mathematical Programming, 45(1): 503-528, 1989.
31. Liu, Y., Jiang, S., and Liao, S. Efficient approximation of cross-validation for kernel methods using Bouligand influence function. In International Conference on Machine Learning (ICML), pp. 324-332, 2014.
32. Martens, J. Deep learning via hessian-free optimization. In International Conference on Machine Learning (ICML), pp. 735-742, 2010.
33. Mei, S. and Zhu, X. The security of latent Dirichlet allocation. In Artificial Intelligence and Statistics (AISTATS), 2015a.
34. Mei, S. and Zhu, X. Using machine teaching to identify optimal training-set attacks on machine learners. In Association for the Advancement of Artificial Intelligence (AAAI), 2015b.
35. Metsis, V., Androutsopoulos, I., and Paliouras, G. Spam filtering with naive Bayes - which naive Bayes? In CEAS, volume 17, pp. 28-69, 2006.
36. Moosavi-Dezfooli, S., Fawzi, A., and Frossard, P. Deep-fool: a simple and accurate method to fool deep neural networks. In Computer Vision and Pattern Recognition (CVPR), pp. 2574-2582, 2016.
37. Pearlmutter, B. A. Fast exact multiplication by the hessian. Neural Computation, 6(1): 147-160, 1994.
38. Ribeiro, M. T., Singh, S., and Guestrin, C. "why should I trust you?": Explaining the predictions of any classifier. In International Conference on Knowledge Discovery and Data Mining (KDD), 2016.
39. Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 115(3): 211-252, 2015.
40. Shrikumar, A., Greenside, P., Shcherbina, A., and Kun-daje, A. Not just a black box: Learning important features through propagating activation differences. arXiv preprint arXiv: 1605.01713, 2016.
41. Simonyan, K., Vcdaldi, A., and Zisserman, A. Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv: 1312.6034, 2013.
42. Springenberg, J. T., Dosovitskiy, A., Brox, T, and Ried-miller, M. Striving for simplicity: The all convolutional net. arXiv preprint arXiv: 1412.6806, 2014.
43. Strack, B., DeShazo, J. P., Gennings, C, Olmo, J. L., Ventura, S., Cios, K. J., and Clore, J. N. Impact of HbAlc measurement on hospital readmission rates: analysis of 70, 000 clinical database patient records. BioMed Research International, 2014, 2014.
44. Szegedy, C, Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. Rethinking the Inception architecture for computer vision. In Computer Vision and Pattern Recognition (CVPR), pp. 2818-2826, 2016.
45. Theano D. Team. Theano: A Python framework for fast computation of mathematical expressions. arXiv preprint arXiv: 1605.02688, 2016.
46. Thomas, W. and Cook, R. D. Assessing influence on predictions from generalized linear models. Technometrics, 32(1): 59-65, 1990.
47. Wei, B, Hu, Y, and Fung, W. Generalized leverage and its applications. Scandinavian Journal of Statistics, 25: 25-37, 1998.
48. Wojnowicz, M., Cruz, B., Zhao, X., Wallace, B., Wolff, M., Luan, J., and Crable, C. "Influence sketching": Finding influential samples in large-scale regressions. arXiv preprint arXiv: 1611.05923, 2016.
49. Van Der Vaart, A. W. Asymptotic statistics. Cambridge University Press, 1998.