Beyond Sparsity: Tree Regularization of Deep Models for Interpretability

The lack of interpretability remains a key barrier to the adoption of deep models in many applications. In this work, we explicitly regularize deep models so human users might step through the process behind their predictions in little time. Specifically, we train deep time-series models so their class-probability predictions have high accuracy while being closely modeled by decision trees with few nodes. Using intuitive toy examples as well as medical tasks for treating sepsis and HIV, we demonstrate that this new tree regularization yields models that are easier for humans to simulate than simpler L1 or L2 penalties without sacrificing predictive power.

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

[2]  Jintanat Ananworanich,et al.  Predictors of disease progression in HIV infection: a review , 2007, AIDS research and therapy.

[3]  Jure Leskovec,et al.  Interpretable Decision Sets: A Joint Framework for Description and Prediction , 2016, KDD.

[4]  Susan Swindells,et al.  Erratum: Adherence to protease inhibitor therapy and outcomes in patients with HIV infection (Annals of Internal Medicine (2000) 133 (21-30)) , 2002 .

[5]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[6]  Carla Teixeira Lopes,et al.  TIMIT Acoustic-Phonetic Continuous Speech Corpus , 2012 .

[7]  Gang Hua,et al.  How to Train a Compact Binary Neural Network with High Accuracy? , 2017, AAAI.

[8]  Jonathan H. Chen,et al.  Machine Learning and Prediction in Medicine - Beyond the Peak of Inflated Expectations. , 2017, The New England journal of medicine.

[9]  Ramprasaath R. Selvaraju,et al.  Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization , 2016 .

[10]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[11]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[12]  Ali Farhadi,et al.  XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks , 2016, ECCV.

[13]  Suresh Venkatasubramanian,et al.  Auditing black-box models for indirect influence , 2016, Knowledge and Information Systems.

[14]  Pascal Vincent,et al.  Visualizing Higher-Layer Features of a Deep Network , 2009 .

[15]  Carlos Guestrin,et al.  Programs as Black-Box Explanations , 2016, ArXiv.

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

[17]  Thomas Lengauer,et al.  Predicting Response to Antiretroviral Treatment by Machine Learning: The EuResist Project , 2012, Intervirology.

[18]  Andrew Slavin Ross,et al.  Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations , 2017, IJCAI.

[19]  Peter Szolovits,et al.  MIMIC-III, a freely accessible critical care database , 2016, Scientific Data.

[20]  Eric P. Xing,et al.  Harnessing Deep Neural Networks with Logic Rules , 2016, ACL.

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

[22]  Shigeru Katagiri,et al.  Automatic node selection for Deep Neural Networks using Group Lasso regularization , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[23]  J. Dinulos,et al.  Acute retroviral syndrome. , 2006, Dermatologic clinics.

[24]  Song Han,et al.  Learning both Weights and Connections for Efficient Neural Network , 2015, NIPS.

[25]  Regina Barzilay,et al.  Rationalizing Neural Predictions , 2016, EMNLP.

[26]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[27]  Héctor Pérez,et al.  Acute retroviral syndrome and high baseline viral load are predictors of rapid HIV progression among untreated Argentinean seroconverters , 2011, Journal of the International AIDS Society.

[28]  Charles Audet,et al.  Blackbox and derivative-free optimization: theory, algorithms and applications , 2016 .

[29]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[30]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[31]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[32]  Peter Szolovits,et al.  Continuous State-Space Models for Optimal Sepsis Treatment: a Deep Reinforcement Learning Approach , 2017, MLHC.

[33]  Jude W. Shavlik,et al.  in Advances in Neural Information Processing , 1996 .

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

[35]  Susan Swindells,et al.  Adherence to Protease Inhibitor Therapy and Outcomes in Patients with HIV Infection , 2000, Annals of Internal Medicine.

[36]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[37]  Rich Caruana,et al.  Model compression , 2006, KDD '06.

[38]  Li Li,et al.  Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records , 2016, Scientific Reports.

[39]  Masashi Sugiyama,et al.  Bayesian Dark Knowledge , 2015 .

[40]  Harris Drucker,et al.  Improving generalization performance using double backpropagation , 1992, IEEE Trans. Neural Networks.

[41]  Walter F. Stewart,et al.  Doctor AI: Predicting Clinical Events via Recurrent Neural Networks , 2015, MLHC.

[42]  Yuchen Zhang,et al.  L1-regularized Neural Networks are Improperly Learnable in Polynomial Time , 2015, ICML.

[43]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[44]  Yan Liu,et al.  Deep Computational Phenotyping , 2015, KDD.

[45]  Scott Lundberg,et al.  An unexpected unity among methods for interpreting model predictions , 2016, ArXiv.

[46]  Vivek Rathod,et al.  Bayesian dark knowledge , 2015, NIPS.