Rule induction for global explanation of trained models

TL;DR

This paper introduces a rule induction method that globally explains trained neural network predictions by capturing feature-class relations, improving interpretability and trust in automated systems.

Contribution

It proposes a novel technique to induce rule sets that explain neural network predictions by integrating feature importance and simplifying input space.

Findings

Achieved macro-averaged F-score of 0.80 on 20 newsgroups dataset

Captured feature-class relations effectively with rule sets

Enhanced interpretability of neural network predictions

Abstract

Understanding the behavior of a trained network and finding explanations for its outputs is important for improving the network's performance and generalization ability, and for ensuring trust in automated systems. Several approaches have previously been proposed to identify and visualize the most important features by analyzing a trained network. However, the relations between different features and classes are lost in most cases. We propose a technique to induce sets of if-then-else rules that capture these relations to globally explain the predictions of a network. We first calculate the importance of the features in the trained network. We then weigh the original inputs with these feature importance scores, simplify the transformed input space, and finally fit a rule induction model to explain the model predictions. We find that the output rule-sets can explain the predictions of a neural network trained for 4-class text classification from the 20 newsgroups dataset to a macro-averaged F-score of 0.80. We make the code available at https://github.com/clips/interpret_with_rules.