A Bayesian Framework for Learning Rule Sets for Interpretable Classification

By Tong Wang, Cynthia Rudin, Finale Doshi-Velez, Yimin Liu, Erica Klampfl, Perry MacNeille. 2017

265 citations recorded by the source corpus.

Subfields: Safety, Robustness & Interpretability, Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Safety, Robustness & Interpretability

In Probabilistic & Bayesian Methods

Citations in the corpus

Learning Optimal and Fair Decision Trees for Non-Discriminative Decision-Making (2019, methodology): “Finally our work relates to interpretable ML, including works on decision rules (Wang et al. 2017; Letham et al. 2015), decision sets (Lakkaraju, Bach, and Jure 2016), and generalized additive models (Lou et al. 2013a).”
Optimal Decision Lists using SAT (2020, methodology): “Here, the proposed approach is compared against sparse versions of decision sets sp and mds2 of (Yu et al. 2020) and optimal sparse decision lists produced by corels (Angelino et al. 2017; Wang et al. 2017).”
Generalized and Scalable Optimal Sparse Decision Trees (2020, background): “, 2018) (FICO), and the mobile advertisement data sets (Wang et al., 2017) (coupon).”
Predictive Multiplicity in Classification (2019, background): “4These are rule-based models that can be expressed as special kinds of linear classifiers, such as decision sets [28], decision lists [3], or and-of-or rules [51].”
Learning customized and optimized lists of rules with mathematical programming (2018, neutral): “ABayesian counterpart to thework of Goh andRudin [26] is that ofWang et al [71], which proves some results analogous to those in Sect.”
Boolean Decision Rules via Column Generation (2018, methodology): “For comparison with our column generation (CG) algorithm, we considered three recently proposed alternatives that also aim to control rule complexity: Bayesian Rule Sets (BRS) (48) and the alternating minimization (AM) and block coordinate descent (BCD) algorithms from (42).”
Learning Optimized Risk Scores (2016, background): “, 2013) and other Boolean functions (see e.g., Malioutov and Varshney, 2013; Wang et al., 2017; Lakkaraju et al., 2016); and other `0-regularized models (Sato et al.”
The Convolutional Tsetlin Machine (2019, background): “Approximate Bayesian approaches have recently been introduced to provide more robust learning of rules [39, 18].”
Designing Fair, Efficient, and Interpretable Policies for Prioritizing Homeless Youth for Housing Resources (2018, methodology): “Many interpretable models have been proposed, including decision rules [29, 14], decision sets [12] and generalized additive models [15, 16].”
Hybrid Decision Making: When Interpretable Models Collaborate With Black-Box Models (2018, methodology): “To decrease the misclassication error, we follow similar steps used in [34].”
Optimal decision trees for categorical data via integer programming (2021, background): “We note that it is possible to enforce “less than or equal to” or “greater than or equal to” form without using the additional variables w, by binarizing numerical features differently, see [8,19].”
A SAT-Based Approach to Learn Explainable Decision Sets (2018, methodology): “Recent approaches include the computation of (smaller or smallest) rule lists [2,42], the computation of decision sets [21], but also the computation of decision trees [3].”
Interpretable Companions for Black-Box Models (2020, methodology): “Our model is different from the current mainstream works in interpretable machine learning that focus on stand-alone interpretable models such as rule-based models [1] and linear models [2], or develops external black-box explanation methods [3, 4] to provide posthoc analysis.”