CGXplain: Rule-Based Deep Neural Network Explanations Using Dual Linear Programs

by   Konstantin Hemker, et al.
University of Cambridge

Rule-based surrogate models are an effective and interpretable way to approximate a Deep Neural Network's (DNN) decision boundaries, allowing humans to easily understand deep learning models. Current state-of-the-art decompositional methods, which are those that consider the DNN's latent space to extract more exact rule sets, manage to derive rule sets at high accuracy. However, they a) do not guarantee that the surrogate model has learned from the same variables as the DNN (alignment), b) only allow to optimise for a single objective, such as accuracy, which can result in excessively large rule sets (complexity), and c) use decision tree algorithms as intermediate models, which can result in different explanations for the same DNN (stability). This paper introduces the CGX (Column Generation eXplainer) to address these limitations - a decompositional method using dual linear programming to extract rules from the hidden representations of the DNN. This approach allows to optimise for any number of objectives and empowers users to tweak the explanation model to their needs. We evaluate our results on a wide variety of tasks and show that CGX meets all three criteria, by having exact reproducibility of the explanation model that guarantees stability and reduces the rule set size by >80 (complexity) at equivalent or improved accuracy and fidelity across tasks (alignment).


page 1

page 2

page 3

page 4


Efficient Decompositional Rule Extraction for Deep Neural Networks

In recent years, there has been significant work on increasing both inte...

Rule Extraction Algorithm for Deep Neural Networks: A Review

Despite the highest classification accuracy in wide varieties of applica...

Computing Rule-Based Explanations by Leveraging Counterfactuals

Sophisticated machine models are increasingly used for high-stakes decis...

Deep Learning for Optimal Volt/VAR Control using Distributed Energy Resources

Given their intermittency, distributed energy resources (DERs) have been...

Measurably Stronger Explanation Reliability via Model Canonization

While rule-based attribution methods have proven useful for providing lo...

NeSyFOLD: A System for Generating Logic-based Explanations from Convolutional Neural Networks

We present a novel neurosymbolic system called NeSyFOLD that classifies ...

Transparent Classification with Multilayer Logical Perceptrons and Random Binarization

Models with transparent inner structure and high classification performa...

Please sign up or login with your details

Forgot password? Click here to reset