Interpretable Machine Learning Tools: A Survey

In recent years machine learning (ML) systems have been deployed extensively in various domains. But most MLbased frameworks lack transparency. To believe in ML models, an individual needs to understand the reasons behind the ML predictions. In this paper, we provide a survey of open-source software tools that help explore and understand the behavior of the ML models. Also, these tools include a variety of interpretable machine learning methods that assist people with understanding the connection between input and output variables through interpretation, validate the decision of a predictive model to enable lucidity, accountability, and fairness in the algorithmic decision making policies. Furthermore, we provide the state-of-the-art of interpretable machine learning (IML) tools, along with a comparison and a brief discussion of the implementation of those IML tools in various programming languages.

[1]  Deepak Venugopal,et al.  DDoS Intrusion Detection Through Machine Learning Ensemble , 2019, 2019 IEEE 19th International Conference on Software Quality, Reliability and Security Companion (QRS-C).

[2]  Frederick T. Sheldon,et al.  Empirical Evaluation of the Ensemble Framework for Feature Selection in DDoS Attack , 2020, 2020 7th IEEE International Conference on Cyber Security and Cloud Computing (CSCloud)/2020 6th IEEE International Conference on Edge Computing and Scalable Cloud (EdgeCom).

[3]  Daniel W. Apley,et al.  Visualizing the effects of predictor variables in black box supervised learning models , 2016, Journal of the Royal Statistical Society: Series B (Statistical Methodology).

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

[5]  Sajjan G. Shiva,et al.  A Holistic Approach for Detecting DDoS Attacks by Using Ensemble Unsupervised Machine Learning , 2020, Advances in Intelligent Systems and Computing.

[6]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

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

[8]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

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

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

[11]  Monotonic Constraints , 2009, Encyclopedia of Database Systems.

[12]  Emil Pitkin,et al.  Peeking Inside the Black Box: Visualizing Statistical Learning With Plots of Individual Conditional Expectation , 2013, 1309.6392.

[13]  Jie Chen,et al.  Explainable Neural Networks based on Additive Index Models , 2018, ArXiv.

[14]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[15]  Amit Dhurandhar,et al.  Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives , 2018, NeurIPS.

[16]  Cynthia Rudin,et al.  Model Class Reliance: Variable Importance Measures for any Machine Learning Model Class, from the "Rashomon" Perspective , 2018 .

[17]  Trevor Hastie,et al.  Regularization Paths for Generalized Linear Models via Coordinate Descent. , 2010, Journal of statistical software.

[18]  Rich Caruana,et al.  InterpretML: A Unified Framework for Machine Learning Interpretability , 2019, ArXiv.

[19]  Sajjan G. Shiva,et al.  A Stealth Migration Approach to Moving Target Defense in Cloud Computing , 2019 .

[20]  Bernd Bischl,et al.  iml: An R package for Interpretable Machine Learning , 2018, J. Open Source Softw..

[21]  Tie-Yan Liu,et al.  LightGBM: A Highly Efficient Gradient Boosting Decision Tree , 2017, NIPS.

[22]  Przemyslaw Biecek,et al.  DALEX: explainers for complex predictive models , 2018, J. Mach. Learn. Res..

[23]  Cynthia Rudin,et al.  Supersparse linear integer models for optimized medical scoring systems , 2015, Machine Learning.

[24]  Carlos Guestrin,et al.  Anchors: High-Precision Model-Agnostic Explanations , 2018, AAAI.

[25]  Amit Dhurandhar,et al.  One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques , 2019, ArXiv.

[26]  Saikat Das,et al.  CoRuM: Collaborative Runtime Monitor Framework for Application Security , 2018, 2018 IEEE/ACM International Conference on Utility and Cloud Computing Companion (UCC Companion).

[27]  Brandon M. Greenwell.  pdp: An R Package for Constructing Partial Dependence Plots , 2017, R J..