Efficient Decompositional Rule Extraction for Deep Neural Networks

by   Mateo Espinosa Zarlenga, et al.
University of Cambridge

In recent years, there has been significant work on increasing both interpretability and debuggability of a Deep Neural Network (DNN) by extracting a rule-based model that approximates its decision boundary. Nevertheless, current DNN rule extraction methods that consider a DNN's latent space when extracting rules, known as decompositional algorithms, are either restricted to single-layer DNNs or intractable as the size of the DNN or data grows. In this paper, we address these limitations by introducing ECLAIRE, a novel polynomial-time rule extraction algorithm capable of scaling to both large DNN architectures and large training datasets. We evaluate ECLAIRE on a wide variety of tasks, ranging from breast cancer prognosis to particle detection, and show that it consistently extracts more accurate and comprehensible rule sets than the current state-of-the-art methods while using orders of magnitude less computational resources. We make all of our methods available, including a rule set visualisation interface, through the open-source REMIX library (https://github.com/mateoespinosa/remix).


page 1

page 2

page 3

page 4


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

Rule-based surrogate models are an effective and interpretable way to ap...

Rule Extraction Algorithm for Deep Neural Networks: A Review

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

Neural Network-Based Rule Models With Truth Tables

Understanding the decision-making process of a machine/deep learning mod...

A Scalable Approach for Facial Action Unit Classifier Training UsingNoisy Data for Pre-Training

Machine learning systems are being used to automate many types of labori...

Polynomial-time Computation via Local Inference Relations

We consider the concept of a local set of inference rules. A local rule ...

Acceleration of Deep Neural Network Training with Resistive Cross-Point Devices

In recent years, deep neural networks (DNN) have demonstrated significan...

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

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

Please sign up or login with your details

Forgot password? Click here to reset