Transparent Classification with Multilayer Logical Perceptrons and Random Binarization

Abstract

Models with transparent inner structure and high classification performance are required to reduce potential risk and provide trust for users in domains like health care, finance, security, etc. However, existing models are hard to simultaneously satisfy the above two properties. In this paper, we propose a new hierarchical rule-based model for classification tasks, named Concept Rule Sets (CRS), which has both a strong expressive ability and a transparent inner structure. To address the challenge of efficiently learning the non-differentiable CRS model, we propose a novel neural network architecture, Multilayer Logical Perceptron (MLLP), which is a continuous version of CRS. Using MLLP and the Random Binarization (RB) method we proposed, we can search the discrete solution of CRS in continuous space using gradient descent and ensure the discrete CRS acts almost the same as the corresponding continuous MLLP. Experiments on 12 public data sets show that CRS outperforms the state-of-the-art approaches and the complexity of the learned CRS is close to the simple decision tree. Source code is available at https://github.com/12wang3/mllp.

arXiv commentAAAI-20 (oral presentation); source codes added

References in corpus (10)

• Distilling the Knowledge in a Neural Network
• Towards A Rigorous Science of Interpretable Machine Learning
• European Union regulations on algorithmic decision-making and a "right to explanation"
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• Understanding Neural Networks Through Deep Visualization
• Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model
• Distilling a Neural Network Into a Soft Decision Tree
• Interpreting CNNs via Decision Trees
• Interpretable Convolutional Neural Networks
• Learning Algorithms via Neural Logic Networks