Awesome Interpretable Machine Learning

• Awesome Interpretable Machine Learning [[https://awesome.re][https://awesome.re/badge.svg]]

Opinionated list of resources facilitating model interpretability (introspection, simplification, visualization, explanation).

** Interpretable Models

• Interpretable models

  • Simple decision trees
  • Rules
  • (Regularized) linear regression
  • k-NN

• (2008) Predictive learning via rule ensembles by Jerome H. Friedman, Bogdan E. Popescu

  • https://dx.doi.org/10.1214/07-AOAS148

• (2014) Comprehensible classification models by Alex A. Freitas

  • https://dx.doi.org/10.1145/2594473.2594475
  • http://www.kdd.org/exploration_files/V15-01-01-Freitas.pdf
  • Interesting discussion of interpretability for a few classification models (decision trees, classification rules, decision tables, nearest neighbors and Bayesian network classifier)

• (2015) Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model by Benjamin Letham, Cynthia Rudin, Tyler H. McCormick, David Madigan

  • https://arxiv.org/pdf/1511.01644
  • https://dx.doi.org/10.1214/15-AOAS848

• (2017) Learning Explanatory Rules from Noisy Data by Richard Evans, Edward Grefenstette

  • https://arxiv.org/pdf/1711.04574

• (2019) Transparent Classification with Multilayer Logical Perceptrons and Random Binarization by Zhuo Wang, Wei Zhang, Ning Liu, Jianyong Wang

  • https://arxiv.org/pdf/1912.04695
  • Code: https://github.com/12wang3/mllp

** Feature Importance

• Models offering feature importance measures

  • Random forest
  • Boosted trees
  • Extremely randomized trees
    • (2006) Extremely randomized trees by Pierre Geurts, Damien Ernst, Louis Wehenkel
      • https://dx.doi.org/10.1007/s10994-006-6226-1
  • Random ferns
    • (2015) rFerns: An Implementation of the Random Ferns Method for General-Purpose Machine Learning by Miron B. Kursa
      • https://dx.doi.org/10.18637/jss.v061.i10
      • https://cran.r-project.org/web/packages/rFerns
      • https://notabug.org/mbq/rFerns
  • Linear regression (with a grain of salt)

• (2007) Bias in random forest variable importance measures: Illustrations, sources and a solution by Carolin Strobl, Anne-Laure Boulesteix, Achim Zeileis, Torsten Hothorn

  • https://dx.doi.org/10.1186/1471-2105-8-25

• (2008) Conditional Variable Importance for Random Forests by Carolin Strobl, Anne-Laure Boulesteix, Thomas Kneib, Thomas Augustin, Achim Zeileis

  • https://dx.doi.org/10.1186/1471-2105-9-307

• (2018) Model Class Reliance: Variable Importance Measures for any Machine Learning Model Class, from the "Rashomon" Perspective by Aaron Fisher, Cynthia Rudin, Francesca Dominici

  • https://arxiv.org/pdf/1801.01489
  • https://github.com/aaronjfisher/mcr
  • Universal (model agnostic) variable importance measure

• (2019) Please Stop Permuting Features: An Explanation and Alternatives by Giles Hooker, Lucas Mentch

  • https://arxiv.org/pdf/1905.03151
  • Paper advocating against feature permutation for importance

• (2018) Visualizing the Feature Importance for Black Box Models by Giuseppe Casalicchio, Christoph Molnar, Bernd Bischl

  • https://arxiv.org/pdf/1804.06620
  • https://github.com/giuseppec/featureImportance
  • Global and local (model agnostic) variable importance measure (based on Model Reliance)

• Very good blog post describing deficiencies of random forest feature importance and the permutation importance

  • http://explained.ai/rf-importance/index.html

• Permutation importance - simple model agnostic approach is described in Eli5 documentation

  • https://eli5.readthedocs.io/en/latest/blackbox/permutation_importance.html

** Feature Selection

• Classification of feature selection methods

  • Filters
  • Wrappers
  • Embedded methods

• (2003) An Introduction to Variable and Feature Selection by Isabelle Guyon, André Elisseeff

  • http://www.jmlr.org/papers/volume3/guyon03a/guyon03a.pdf
  • Be sure to read this very illustrative introduction to feature selection

• Filter Methods

  • (2006) On the Use of Variable Complementarity for Feature Selection in Cancer Classification by Patrick Meyer, Gianluca Bontempi

    • https://dx.doi.org/10.1007/11732242_9
    • https://pdfs.semanticscholar.org/d72f/f5063520ce4542d6d9b9e6a4f12aafab6091.pdf
    • Introduces information theoretic methods - double input symmetrical relevance (DISR)

  • (2012) Conditional Likelihood Maximisation: A Unifying Framework for Information Theoretic Feature Selection by Gavin Brown, Adam Pocock, Ming-Jie Zhao, Mikel Luján

    • http://www.jmlr.org/papers/volume13/brown12a/brown12a.pdf
    • Code: https://github.com/Craigacp/FEAST
    • Discusses various approaches based on mutual information (MIM, mRMR, MIFS, CMIM, JMI, DISR, ICAP, CIFE, CMI)

  • (2012) Feature selection via joint likelihood by Adam Pocock

    • http://www.cs.man.ac.uk/~gbrown/publications/pocockPhDthesis.pdf

  • (2017) Relief-Based Feature Selection: Introduction and Review by Ryan J. Urbanowicz, Melissa Meeker, William LaCava, Randal S. Olson, Jason H. Moore

    • https://arxiv.org/pdf/1711.08421

  • (2017) Benchmarking Relief-Based Feature Selection Methods for Bioinformatics Data Mining by Ryan J. Urbanowicz, Randal S. Olson, Peter Schmitt, Melissa Meeker, Jason H. Moore

    • https://arxiv.org/pdf/1711.08477

• Wrapper methods

  • (2015) Feature Selection with theBorutaPackage by Miron B. Kursa, Witold R. Rudnicki

    • https://dx.doi.org/10.18637/jss.v036.i11
    • https://cran.r-project.org/web/packages/Boruta/
    • Code (official, R): https://notabug.org/mbq/Boruta/
    • Code (Python): https://github.com/scikit-learn-contrib/boruta_py

  • Boruta for those in a hurry

    • https://cran.r-project.org/web/packages/Boruta/vignettes/inahurry.pdf

• General

  • (1994) Irrelevant Features and the Subset Selection Problem by George John, Ron Kohavi, Karl Pfleger

    • https://pdfs.semanticscholar.org/a83b/ddb34618cc68f1014ca12eef7f537825d104.pdf
    • Classic paper discussing weakly relevant features, irrelevant features, strongly relevant features

  • (2003) Special issue of JMLR of feature selection - oldish (2003)

    • http://www.jmlr.org/papers/special/feature03.html

  • (2004) Result Analysis of the NIPS 2003 Feature Selection Challenge by Isabelle Guyon, Steve Gunn, Asa Ben-Hur, Gideon Dror

    • Paper: https://papers.nips.cc/paper/2728-result-analysis-of-the-nips-2003-feature-selection-challenge.pdf
    • Website http://clopinet.com/isabelle/Projects/NIPS2003/

  • (2007) Consistent Feature Selection for Pattern Recognition in Polynomial Time by Roland Nilsson, José Peña, Johan Björkegren, Jesper Tegnér

    • http://www.jmlr.org/papers/volume8/nilsson07a/nilsson07a.pdf
    • Discusses minimal optimal vs all-relevant approaches to feature selection

• Feature Engineering and Selection by Kuhn & Johnson

  • Sligtly off-topic, but very interesting book
  • http://www.feat.engineering/index.html
  • https://bookdown.org/max/FES/
  • https://github.com/topepo/FES

• Feature Engineering presentation by H. J. van Veen

  • Slightly off-topicm but very interesting deck of slides
  • Slides: https://www.slideshare.net/HJvanVeen/feature-engineering-72376750

** Model Explanations *** Philosophy + Magnets by R. P. Feynman https://www.youtube.com/watch?v=wMFPe-DwULM

+ (2002) Looking Inside the Black Box, presentation of Leo Breiman
  + https://www.stat.berkeley.edu/users/breiman/wald2002-2.pdf

+ (2011) To Explain or to Predict? by Galit Shmueli
  + https://arxiv.org/pdf/1101.0891
  + https://dx.doi.org/10.1214/10-STS330

+ (2016) The Mythos of Model Interpretability by Zachary C. Lipton
  + https://arxiv.org/pdf/1606.03490
  + https://www.youtube.com/watch?v=mvzBQci04qA

+ (2017) Towards A Rigorous Science of Interpretable Machine Learning by Finale Doshi-Velez, Been Kim
  + https://arxiv.org/pdf/1702.08608

+ (2017) The Promise and Peril of Human Evaluation for Model Interpretability by Bernease Herman
  + https://arxiv.org/pdf/1711.07414

+ (2018) [[http://bayes.cs.ucla.edu/WHY/why-intro.pdf][The Book of Why: The New Science of Cause and Effect]] by Judea Pearl

+ (2018) Please Stop Doing the "Explainable" ML by Cynthia Rudin
  + Video (starts 17:30, lasts 10 min): https://zoom.us/recording/play/0y-iI9HamgyDzzP2k_jiTu6jB7JgVVXnjWZKDMbnyRTn3FsxTDZy6Wkrj3_ekx4J
  + Linked at: https://users.cs.duke.edu/~cynthia/mediatalks.html

+ (2018) Explaining Explanations: An Approach to Evaluating Interpretability of Machine Learning by Leilani H. Gilpin, David Bau, Ben Z. Yuan, Ayesha Bajwa, Michael Specter, Lalana Kagal
  + https://arxiv.org/pdf/1806.00069

+ (2019) Interpretable machine learning: definitions, methods, and applications by W. James Murdoch, Chandan Singh, Karl Kumbier, Reza Abbasi-Asl, Bin Yu
  + https://arxiv.org/pdf/1901.04592

+ (2019) On Explainable Machine Learning Misconceptions A More Human-Centered Machine Learning by Patrick Hall
  + https://github.com/jphall663/xai_misconceptions/blob/master/xai_misconceptions.pdf
  + https://github.com/jphall663/xai_misconceptions

+ (2019) An Introduction to Machine Learning Interpretability. An Applied Perspective on Fairness, Accountability, Transparency, and Explainable AI by Patrick Hall and Navdeep Gill
  + https://www.h2o.ai/wp-content/uploads/2019/08/An-Introduction-to-Machine-Learning-Interpretability-Second-Edition.pdf

*** Model Agnostic Explanations + (2009) How to Explain Individual Classification Decisions by David Baehrens, Timon Schroeter, Stefan Harmeling, Motoaki Kawanabe, Katja Hansen, Klaus-Robert Mueller + https://arxiv.o