# Learning Decision Trees Recurrently Through Communication

arXiv: https://arxiv.org/abs/1902.01780 · HTML: https://mlsanity.com/paper/1902.01780/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Feb 2019.

## Built on by (most cited first, 3 of 3)

- [Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning](https://mlsanity.com/paper/2106.03921/) (2021)
- [Rationalization through Concepts](https://mlsanity.com/paper/2105.04837/) (2021)
- [Making CNNs Interpretable by Building Dynamic Sequential Decision Forests with Top-down Hierarchy Learning](https://mlsanity.com/paper/2106.02824/) (2021)

## Abstract (arXiv)

Integrated interpretability without sacrificing the prediction accuracy of decision making algorithms has the potential of greatly improving their value to the user. Instead of assigning a label to an image directly, we propose to learn iterative binary sub-decisions, inducing sparsity and transparency in the decision making process. The key aspect of our model is its ability to build a decision tree whose structure is encoded into the memory representation of a Recurrent Neural Network jointly learned by two models communicating through message passing. In addition, our model assigns a semantic meaning to each decision in the form of binary attributes, providing concise, semantic and relevant rationalizations to the user. On three benchmark image classification datasets, including the large-scale ImageNet, our model generates human interpretable binary decision sequences explaining the predictions of the network while maintaining state-of-the-art accuracy.