InterpretML: A Unified Framework for Machine Learning Interpretability

Abstract

InterpretML is an open-source Python package which exposes machine learning interpretability algorithms to practitioners and researchers. InterpretML exposes two types of interpretability - glassbox models, which are machine learning models designed for interpretability (ex: linear models, rule lists, generalized additive models), and blackbox explainability techniques for explaining existing systems (ex: Partial Dependence, LIME). The package enables practitioners to easily compare interpretability algorithms by exposing multiple methods under a unified API, and by having a built-in, extensible visualization platform. InterpretML also includes the first implementation of the Explainable Boosting Machine, a powerful, interpretable, glassbox model that can be as accurate as many blackbox models. The MIT licensed source code can be downloaded from github.com/microsoft/interpret.

References in corpus (2)

• Scikit-learn: Machine Learning in Python
• An Interpretable Model with Globally Consistent Explanations for Credit Risk

Cited by in corpus (52)

• Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges
• Interpretable and Explainable Machine Learning for Materials Science and Chemistry
• Explainable, Interpretable & Trustworthy AI for Intelligent Digital Twin: Case Study on Remaining Useful Life
• Neural Additive Models: Interpretable Machine Learning with Neural Nets
• Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions
• A Survey of Deep Learning for Scientific Discovery
• The Grammar of Interactive Explanatory Model Analysis
• Considerations When Learning Additive Explanations for Black-Box Models
• dalex: Responsible Machine Learning with Interactive Explainability and Fairness in Python
• StickyLand: Breaking the Linear Presentation of Computational Notebooks
• Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and Values
• A Novel Tropical Geometry-based Interpretable Machine Learning Method: Application in Prognosis of Advanced Heart Failure
• GAM Coach: Towards Interactive and User-centered Algorithmic Recourse
• Coalesced Multi-Output Tsetlin Machines with Clause Sharing
• GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactions
• Interpretable Predictive Models to Understand Risk Factors for Maternal and Fetal Outcomes
• Fooling Partial Dependence via Data Poisoning
• NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning
• The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models
• Making the black-box brighter: interpreting machine learning algorithm for forecasting drilling accidents
• An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services
• Impact of Accuracy on Model Interpretations
• Reliable Feature Selection for Adversarially Robust Cyber-Attack Detection
• From Point to probabilistic gradient boosting for claim frequency and severity prediction
• In Search of netUnicorn: A Data-Collection Platform to Develop Generalizable ML Models for Network Security Problems
• TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
• Purifying Interaction Effects with the Functional ANOVA: An Efficient Algorithm for Recovering Identifiable Additive Models
• Accuracy, Interpretability, and Differential Privacy via Explainable Boosting
• Automation of Quantum Dot Measurement Analysis via Explainable Machine Learning
• Explanations Based on Item Response Theory (eXirt): A Model-Specific Method to Explain Tree-Ensemble Model in Trust Perspective
• ControlBurn: Feature Selection by Sparse Forests
• RecRec: Algorithmic Recourse for Recommender Systems
• The Thousand Faces of Explainable AI Along the Machine Learning Life Cycle: Industrial Reality and Current State of Research
• Vehicle Fuel Optimization Under Real-World Driving Conditions: An Explainable Artificial Intelligence Approach
• On marginal feature attributions of tree-based models
• Framing Algorithmic Recourse for Anomaly Detection
• Exploring Factors Affecting Student Learning Satisfaction during COVID-19 in South Korea
• Enabling Machine Learning Algorithms for Credit Scoring -- Explainable Artificial Intelligence (XAI) methods for clear understanding complex predictive models
• Extractive Text Summarization Using Generalized Additive Models with Interactions for Sentence Selection
• Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical Context
• What Would You Ask the Machine Learning Model? Identification of User Needs for Model Explanations Based on Human-Model Conversations
• Interpretability of machine-learning models in physical sciences
• A Comparative Approach to Explainable Artificial Intelligence Methods in Application to High-Dimensional Electronic Health Records: Examining the Usability of XAI
• How Interpretable and Trustworthy are GAMs?
• Ensembles of Random SHAPs
• It's FLAN time! Summing feature-wise latent representations for interpretability
• Predicting Census Survey Response Rates With Parsimonious Additive Models and Structured Interactions
• A Unified and Fast Interpretable Model for Predictive Analytics
• Interpretable, Physics-Informed Learning Reveals Sulfur Adsorption and Poisoning Mechanisms in 13-Atom Icosahedra Nanoclusters
• TrustyAI Explainability Toolkit
• Axiomatic Explanations for Visual Search, Retrieval, and Similarity Learning
• Neural Additive and Basis Models with Feature Selection and Interactions