Regional Tree Regularization for Interpretability in Black Box Models
arXiv:1908.04494
Abstract
The lack of interpretability remains a barrier to the adoption of deep neural networks. Recently, tree regularization has been proposed to encourage deep neural networks to resemble compact, axis-aligned decision trees without significant compromises in accuracy. However, it may be unreasonable to expect that a single tree can predict well across all possible inputs. In this work, we propose regional tree regularization, which encourages a deep model to be well-approximated by several separate decision trees specific to predefined regions of the input space. Practitioners can define regions based on domain knowledge of contexts where different decision-making logic is needed. Across many datasets, our approach delivers more accurate predictions than simply training separate decision trees for each region, while producing simpler explanations than other neural net regularization schemes without sacrificing predictive power. Two healthcare case studies in critical care and HIV demonstrate how experts can improve understanding of deep models via our approach.
arXiv commentAAAI 2020 (Oral)
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Playing Atari with Deep Reinforcement Learning
- Methods for Interpreting and Understanding Deep Neural Networks
- Understanding Black-box Predictions via Influence Functions
- From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification
- Grad-CAM: Why did you say that?
- Distilling a Neural Network Into a Soft Decision Tree
- Distilling Knowledge from Deep Networks with Applications to Healthcare Domain
- Beyond Sparsity: Tree Regularization of Deep Models for Interpretability
- Programs as Black-Box Explanations