Fetching the paper…
Reading the bibliography…
How can we explain the predictions of a black-box model? In this paper, we use influence functions -- a classic technique from robust statistics -- to trace a model's prediction through the learning algorithm and back to its training data, thereby identifying training points most responsible for a given prediction.
The infinitesimal jackknife
Jaeckel, L. A · 1972
Earlier work this paper cites.
The influence curve and its role in robust estimation
Hampel, F. R · 1974
Earlier work this paper cites.
Detection of influential observation in linear regression
Cook, R. D · 1977
Earlier work this paper cites.
Characterizations of an empirical influence function for detecting influential cases in regression
Cook, R. D. and Weisberg, S · 1980
Earlier work this paper cites.
Logistic regression diagnostics
Pregibon, D. et al · 1981
Earlier work this paper cites.
Residuals and influence in regression
Cook, R. D. and Weisberg, S · 1982
Earlier work this paper cites.
Influential observations, high leverage points, and outliers in linear regression
Chatterjee, S. and Hadi, A. S · 1986
Earlier work this paper cites.
Assessment of local influence
Cook, R. D · 1986
Earlier work this paper cites.
Robust Statistics: The Approach Based on Influence Functions
Hampel, F. R., Ronchetti, E. M., Rousseeuw, P. J., and Stahel, W. A · 1986
Earlier work this paper cites.
On the limited memory BFGS method for large scale optimization
Liu, D. C. and Nocedal, J · 1989
Earlier work this paper cites.
Assessing influence on predictions from generalized linear models
Thomas, W. and Cook, R. D · 1990
Earlier work this paper cites.
Fast exact multiplication by the Hessian
Pearlmutter, B. A · 1994
Earlier work this paper cites.
Gradient-based learning applied to document recognition
LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P · 1998
Earlier work this paper cites.
Asymptotic statistics
van der Vaart, A. W · 1998
Earlier work this paper cites.
Generalized leverage and its applications
Wei, B., Hu, Y., and Fung, W · 1998
Earlier work this paper cites.
On robustness properties of convex risk minimization methods for pattern recognition
Christmann, A. and Steinwart, I · 2004
Earlier work this paper cites.
Spam filtering with naive Bayes – which naive Bayes?
Metsis, V., Androutsopoulos, I., and Paliouras, G · 2006
Earlier work this paper cites.
Model selection in kernel based regression using the influence function
Debruyne, M., Hubert, M., and Suykens, J. A · 2008
Cited alongside, same era.
A theory of learning from different domains
Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., and Vaughan, J. W · 2010
Cited alongside, same era.
Deep learning via hessian-free optimization
Martens, J · 2010
Cited alongside, same era.
Support vector machines under adversarial label noise
Biggio, B., Nelson, B., and Laskov, P · 2011
Cited alongside, same era.
Adversarial machine learning
Huang, L., Joseph, A. D., Nelson, B., Rubinstein, B. I., and Tygar, J · 2011
Cited alongside, same era.
Risk prediction models for hospital readmission: a systematic review
Kansagara, D., Englander, H., Salanitro, A., Kagen, D., Theobald, C., Freeman, M., and Kripalani, S · 2011
Cited alongside, same era.
Keras , 2015
Chollet, F · 2015
Later among the works it cites.
Explaining and harnessing adversarial examples
Goodfellow, I. J., Shlens, J., and Szegedy, C · 2015
Later among the works it cites.
Understanding classifier errors by examining influential neighbors
Kabra, M., Robie, A., and Branson, K · 2015
Later among the works it cites.
Adam: A method for stochastic optimization
Kingma, D. and Ba, J · 2015
Later among the works it cites.
ImageNet large scale visual recognition challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al · 2015
Later among the works it cites.
Auditing black-box models for indirect influence
Adler, P., Falk, C., Friedler, S. A., Rybeck, G., Scheidegger, C., Smith, B., and Venkatasubramanian, S · 2016
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Poisoning attacks against support vector machines
Biggio, B., Nelson, B., and Laskov, P · 2012
Cited alongside, same era.
Imagenet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., and Hinton, G. E · 2012
Cited alongside, same era.
Deep inside convolutional networks: Visualising image classification models and saliency maps
Simonyan, K., Vedaldi, A., and Zisserman, A · 2013
Cited alongside, same era.
Decaf: A deep convolutional activation feature for generic visual recognition
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., and Darrell, T · 2014
Cited alongside, same era.
Classification in the presence of label noise: a survey
Frénay, B. and Verleysen, M · 2014
Cited alongside, same era.
Efficient approximation of cross-validation for kernel methods using Bouligand influence function
Liu, Y., Jiang, S., and Liao, S · 2014
Cited alongside, same era.
Later among the works it cites.
Second order stochastic optimization in linear time
Agarwal, N., Bullins, B., and Hazan, E · 2016
Later among the works it cites.
Debugging machine learning models
Cadamuro, G., Gilad-Bachrach, R., and Zhu, X · 2016
Later among the works it cites.
Algorithmic transparency via quantitative input influence: Theory and experiments with learning systems
Datta, A., Sen, S., and Zick, Y · 2016
Later among the works it cites.
European union regulations on algorithmic decision-making and a “right to explanation”
Goodman, B. and Flaxman, S · 2016
Later among the works it cites.
Deepfool: a simple and accurate method to fool deep neural networks
Moosavi-Dezfooli, S., Fawzi, A., and Frossard, P · 2016
Later among the works it cites.
”Why Should I Trust You?”: Explaining the predictions of any classifier
Ribeiro, M. T., Singh, S., and Guestrin, C · 2016
Later among the works it cites.
Rethinking the Inception architecture for computer vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z · 2016
Later among the works it cites.
Theano: A Python framework for fast computation of mathematical expressions
Theano D. Team · 2016
Later among the works it cites.
“Influence sketching”: Finding influential samples in large-scale regressions
Wojnowicz, M., Cruz, B., Zhao, X., Wallace, B., Wolff, M., Luan, J., and Crable, C · 2016
Later among the works it cites.
Learning important features through propagating activation differences
Shrikumar, A., Greenside, P., and Kundaje, A · 2017
Closest in time.