Efficient Decompositional Rule Extraction for Deep Neural NetworksDownload PDF

21 Sept 2021, 14:51 (edited 15 Nov 2021)XAI 4 Debugging Workshop @ NEURIPS 2021 PosterReaders: Everyone
  • Keywords: Explainable Artificial Intelligence, Deep Learning, Rule Extraction, Interpretability, Debuggability, XAI, Neural Networks
  • TL;DR: We propose, to the best of our knowledge, the first polynomial-time decompositional rule extraction algorithm for deep neural networks.
  • Abstract: 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).
0 Replies