Interpretable Rule Discovery Through Bilevel Optimization of Split-Rules of Nonlinear Decision Trees for Classification Problems

  title={Interpretable Rule Discovery Through Bilevel Optimization of Split-Rules of Nonlinear Decision Trees for Classification Problems},
  author={Yashesh D. Dhebar and Kalyanmoy Deb},
  journal={IEEE Transactions on Cybernetics},
For supervised classification problems involving design, control, and other practical purposes, users are not only interested in finding a highly accurate classifier but they also demand that the obtained classifier be easily interpretable. While the definition of interpretability of a classifier can vary from case to case, here, by a humanly interpretable classifier, we restrict it to be expressed in simplistic mathematical terms. As a novel approach, we represent a classifier as an assembly… 

Evaluating Nonlinear Decision Trees for Binary Classification Tasks with Other Existing Methods

The study reveals key issues such as effect of classification on the method’s parameter values, complexity of the classifier versus achieved accuracy, and interpretability of resulting classifiers.

Handling Imbalanced Classification Problems With Support Vector Machines via Evolutionary Bilevel Optimization

The experimental results provided evidence of the effectiveness of EBCS-SVM when working with highly imbalanced datasets, and the proposed method is assessed using 70 datasets of imbalanced classification and compared with several state-of-the-art methods.

An Explainable Classifier based on Genetically Evolved Graph Structures

An evolutionary algorithm and genetic operators to evolve both, vertex and edge sets, enhancing the search space of possible AbDG structures are proposed and the proposed method outperforms GA-AbDG and five other classical interpretable classification algorithms.

Interpretable-AI Policies using Evolutionary Nonlinear Decision Trees for Discrete Action Systems

This article uses a recently proposed nonlinear decision-tree (NLDT) approach to find a hierarchical set of control rules in an attempt to maximize the open-loop performance for approximating and explaining the pretrained black-box DRL (oracle) agent using the labeled state-action dataset.

REM: An Integrative Rule Extraction Methodology for Explainable Data Analysis in Healthcare

It is demonstrated that REM efficiently extracts accurate, comprehensible rulesets from deep neural networks that can be readily integrated with rulesets obtained from tree-based approaches and enables the clinicians to validate and calibrate the extracted rulesets with their domain knowledge.

Interpretable AI Agent Through Nonlinear Decision Trees for Lane Change Problem

This study applies a previously proposed nonlinear decision tree (NLDT) framework to the lane changing problem involving six critical cars in front and rear in left, middle, and right lanes of a pilot car and makes a scratch to the issue of interpretability of modern machine learning based tools.

Complexity in Data-Driven Fuzzy Inference Systems: Survey, Classification and Perspective

A systematic literature review of 1340 scientific papers published between 1991 and 2019 on the topic of FIS complexity issues found key FIS quality attributes found are performance, accuracy, efficiency, and interpretability.

Evaluating Performance Metrics in Classifying Bitcoin Mixing Services Using Decision Tree Algorithm

Using time-frequency analysis, features can be recovered at the network, account, or transaction level to create attributed temporal heterogeneous network Motifs and characterize many forms of address patterns.

Extraction of Space Containing Noise and Forecast of Complex Data by Multiway Tree Bi-Level GA

In this study, the sample space was divided into a highly versatile space and a low versatility space by using the globally optimal decision tree, and it was confirmed that the prediction accuracy improved when the binary tree was changed to the ternary tree.



An interpretable classification rule mining algorithm

Polynomial-fuzzy decision tree structures for classifying medical data

The Truth is In There - Rule Extraction from Opaque Models Using Genetic Programming

This study shows how the gap between accuracy and other aspects can be bridged by using a rule extraction method (termed G-REX) based on genetic programming, capable of extracting both accurate and comprehensible representations, thus allowing high performance also in domains where comprehensibility is of essence.

Rule extraction from linear support vector machines

The ability to convert SVM's and other "black-box" classifiers into a set of human-understandable rules, is critical not only for physician acceptance, but also to reducing the regulatory barrier for medical-decision support systems based on such classifiers.

Classification and regression trees

  • W. Loh
  • Computer Science
    WIREs Data Mining Knowl. Discov.
  • 2011
This article gives an introduction to the subject of classification and regression trees by reviewing some widely available algorithms and comparing their capabilities, strengths, and weakness in two examples.

Comprehensible Credit Scoring Models Using Rule Extraction from Support Vector Machines

This paper provides an overview of the recently proposed rule extraction techniques for SVMs and introduces two others taken from the artificial neural networks domain, being Trepan and G-REX, which rank at the top of comprehensible classification techniques.

Improving Induction of Linear Classification Trees with Genetic Programming

Results indicate that GP can be applied successfully to classification problems and fitness sharing Pareto works better than domination Pare to, and areas of future research are identified.

A System for Induction of Oblique Decision Trees

This system, OC1, combines deterministic hill-climbing with two forms of randomization to find a good oblique split (in the form of a hyperplane) at each node of a decision tree.

Applying genetic programming technique in classification trees

Two new genetic operators, elimination and merge, are designed in the proposed approach to remove redundancy and subsumption, thus producing more accurate and concise decision rules than that without using them.