Explaining Deep Learning Models - A Bayesian Non-parametric Approach

Understanding and interpreting how machine learning (ML) models make decisions have been a big challenge. While recent research has proposed various technical approaches to provide some clues as to how an ML model makes individual predictions, they cannot provide users with an ability to inspect a model as a complete entity. In this work, we propose a novel technical approach that augments a Bayesian non-parametric regression mixture model with multiple elastic nets. Using the enhanced mixture model, we can extract generalizable insights for a target model through a global approximation. To demonstrate the utility of our approach, we evaluate it on different ML models in the context of image recognition. The empirical results indicate that our proposed approach not only outperforms the state-of-the-art techniques in explaining individual decisions but also provides users with an ability to discover the vulnerabilities of the target ML models.

[1]  Mike Wu,et al.  Beyond Sparsity: Tree Regularization of Deep Models for Interpretability , 2017, AAAI.

[2]  Cliburn Chan,et al.  Understanding GPU Programming for Statistical Computation: Studies in Massively Parallel Massive Mixtures , 2010, Journal of computational and graphical statistics : a joint publication of American Statistical Association, Institute of Mathematical Statistics, Interface Foundation of North America.

[3]  Abhishek Das,et al.  Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[4]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

[5]  Qing Li,et al.  The Bayesian elastic net , 2010 .

[6]  Ken Lang,et al.  NewsWeeder: Learning to Filter Netnews , 1995, ICML.

[7]  Adrian F. M. Smith,et al.  Bayesian computation via the gibbs sampler and related markov chain monte carlo methods (with discus , 1993 .

[8]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[9]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[10]  Faming Liang,et al.  A Bootstrap Metropolis–Hastings Algorithm for Bayesian Analysis of Big Data , 2016, Technometrics.

[11]  Yi Yang,et al.  DevNet: A Deep Event Network for multimedia event detection and evidence recounting , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Ankur Taly,et al.  Gradients of Counterfactuals , 2016, ArXiv.

[13]  Percy Liang,et al.  Understanding Black-box Predictions via Influence Functions , 2017, ICML.

[14]  Volkan Cevher,et al.  WASP: Scalable Bayes via barycenters of subset posteriors , 2015, AISTATS.

[15]  Yann LeCun,et al.  The mnist database of handwritten digits , 2005 .

[16]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[17]  Mike West,et al.  Efficient Classification-Based Relabeling in Mixture Models , 2011, The American statistician.

[18]  Yarin Gal,et al.  Real Time Image Saliency for Black Box Classifiers , 2017, NIPS.

[19]  David B. Dunson,et al.  The Multiple Bayesian Elastic Net , 2010 .

[20]  Daniel Jurafsky,et al.  Understanding Neural Networks through Representation Erasure , 2016, ArXiv.

[21]  Andrea Vedaldi,et al.  Interpretable Explanations of Black Boxes by Meaningful Perturbation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[22]  Chris Hans Elastic Net Regression Modeling With the Orthant Normal Prior , 2011 .

[23]  Lancelot F. James,et al.  Gibbs Sampling Methods for Stick-Breaking Priors , 2001 .

[24]  Zachary Chase Lipton The mythos of model interpretability , 2016, ACM Queue.

[25]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[26]  Avanti Shrikumar,et al.  Learning Important Features Through Propagating Activation Differences , 2017, ICML.

[27]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[28]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[29]  Alexander Binder,et al.  On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation , 2015, PloS one.

[30]  Jean-Michel Marin,et al.  Bayesian Modelling and Inference on Mixtures of Distributions , 2005 .

[31]  Max Welling,et al.  Visualizing Deep Neural Network Decisions: Prediction Difference Analysis , 2017, ICLR.

[32]  Oluwasanmi Koyejo,et al.  Examples are not enough, learn to criticize! Criticism for Interpretability , 2016, NIPS.

[33]  Geoffrey E. Hinton,et al.  Distilling a Neural Network Into a Soft Decision Tree , 2017, CEx@AI*IA.

[34]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[35]  Christian Hennig,et al.  Methods for merging Gaussian mixture components , 2010, Adv. Data Anal. Classif..

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