Explaining Deep Learning Models using Causal Inference

Although deep learning models have been successfully applied to a variety of tasks, due to the millions of parameters, they are becoming increasingly opaque and complex. In order to establish trust for their widespread commercial use, it is important to formalize a principled framework to reason over these models. In this work, we use ideas from causal inference to describe a general framework to reason over CNN models. Specifically, we build a Structural Causal Model (SCM) as an abstraction over a specific aspect of the CNN. We also formulate a method to quantitatively rank the filters of a convolution layer according to their counterfactual importance. We illustrate our approach with popular CNN architectures such as LeNet5, VGG19, and ResNet32.

[1]  Anupam Datta,et al.  Gender Bias in Neural Natural Language Processing , 2018, Logic, Language, and Security.

[2]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[3]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[4]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Ronald M. Summers,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, IEEE Transactions on Medical Imaging.

[6]  Matt J. Kusner,et al.  Counterfactual Fairness , 2017, NIPS.

[7]  J. Pearl.  Causal inference in statistics: An overview , 2009 .

[8]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[9]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[10]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Guy Lemieux,et al.  DropBack: Continuous Pruning During Training , 2018, ArXiv.

[12]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[13]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[14]  Dean Pomerleau,et al.  Efficient Training of Artificial Neural Networks for Autonomous Navigation , 1991, Neural Computation.

[15]  Bernhard Schölkopf,et al.  Modeling confounding by half-sibling regression , 2016, Proceedings of the National Academy of Sciences.

[16]  Cheng Soon Ong,et al.  A Primer on Causal Analysis , 2018, ArXiv.

[17]  Bernhard Schölkopf,et al.  Elements of Causal Inference: Foundations and Learning Algorithms , 2017 .

[18]  Rajat Raina,et al.  Large-scale deep unsupervised learning using graphics processors , 2009, ICML '09.

[19]  Brian E. Ruttenberg,et al.  Causal Learning and Explanation of Deep Neural Networks via Autoencoded Activations , 2018, ArXiv.

[20]  Jack W. Stokes,et al.  Large-scale malware classification using random projections and neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[21]  Jing Wang,et al.  A fast deep learning system using GPU , 2014, 2014 IEEE International Symposium on Circuits and Systems (ISCAS).

[22]  Andrew Y. Ng,et al.  Reading Digits in Natural Images with Unsupervised Feature Learning , 2011 .

[23]  Joaquin Quiñonero Candela,et al.  Counterfactual reasoning and learning systems: the example of computational advertising , 2013, J. Mach. Learn. Res..