Abstract

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 to maintain accuracy OR
2. sacrifice accuracy to maintain interpretability.

We forgo this dilemma by proposing 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 both:

1. improved accuracy: NBDTs match or outperform modern neural networks on CIFAR, ImageNet and better generalize to unseen classes byup to 16%. Furthermore, our surrogate loss improves the original model’s accuracy by up to 2%
2. improved interpretability: improving human trust by clearly identifying model mistakes and assisting in dataset debugging

Code and pretrained NBDTs are on Github.

Takeaways

Our work culminates in three key contributions that you can takeaway for future research:

• Our Neural-Backed Decision Tree achieves accuracy competitive with then-state-of-the-art neural network EfficientNet on ImageNet, maintaining interpretable properties, showing accuracy and interpretability can be jointly improved.
• Hierarchical softmax is known to hurt accuracy. We thus instead develop and use a Tree Supervision Loss, demonstrating hierarchical softmax is not the only way to train a hierarchical classifier.
• Our Induced Hierarchy, built from the weights of a pretrained neural network, outperforms existing taxonomies (e.g., WordNet) and data-based hierarchies (e.g., using information gain), demonstrating a hierarchy built-in weight space is most effective.

Getting Started

Installation is just one line.

pip install nbdt

Run on any image of your choosing.

nbdt https://bit.ly/3eiuCId