NBDT: Neural-Backed Decision Trees
This addresses the need for accurate and interpretable models in high-stakes domains like finance and medicine, offering a novel approach that avoids the typical sacrifices of previous methods.
The paper tackles the trade-off between accuracy and interpretability in deep learning by introducing Neural-Backed Decision Trees (NBDTs), which match or outperform modern neural networks on datasets like CIFAR and ImageNet, with up to 16% better generalization to unseen classes and up to 2% accuracy improvement from a surrogate loss.
Machine learning applications such as finance and medicine demand accurate and justifiable predictions, barring most deep learning methods from use. In response, previous work combines decision trees with deep learning, yielding models that (1) sacrifice interpretability for accuracy or (2) sacrifice accuracy for interpretability. We forgo this dilemma by jointly improving accuracy and interpretability using Neural-Backed Decision Trees (NBDTs). NBDTs replace a neural network's final linear layer with a differentiable sequence of decisions and a surrogate loss. This forces the model to learn high-level concepts and lessens reliance on highly-uncertain decisions, yielding (1) accuracy: NBDTs match or outperform modern neural networks on CIFAR, ImageNet and better generalize to unseen classes by up to 16%. Furthermore, our surrogate loss improves the original model's accuracy by up to 2%. NBDTs also afford (2) interpretability: improving human trustby clearly identifying model mistakes and assisting in dataset debugging. Code and pretrained NBDTs are at https://github.com/alvinwan/neural-backed-decision-trees.