# DecisioNet: A Binary-Tree Structured Neural Network

arXiv: https://arxiv.org/abs/2207.01127 · HTML: https://mlsanity.com/paper/2207.01127/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 3 Jul 2022.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [Distilling a Neural Network Into a Soft Decision Tree](https://mlsanity.com/paper/1711.09784/) (2017)
- [Adaptive Neural Trees](https://mlsanity.com/paper/1807.06699/) (2018)
- [The Tree Ensemble Layer: Differentiability meets Conditional Computation](https://mlsanity.com/paper/2002.07772/) (2020)
- [You Look Twice: GaterNet for Dynamic Filter Selection in CNNs](https://mlsanity.com/paper/1811.11205/) (2018)
- [Discrete Autoencoders for Sequence Models](https://mlsanity.com/paper/1801.09797/) (2018)
- [Decision Forests, Convolutional Networks and the Models in-Between](https://mlsanity.com/paper/1603.01250/) (2016)
- [Self-Adaptive Network Pruning](https://mlsanity.com/paper/1910.08906/) (2019)
- [End-to-end Learning of Deterministic Decision Trees](https://mlsanity.com/paper/1712.02743/) (2017)

## Built on by (most cited first, 1 of 1)

- [Sigma-Branch: Hierarchical Single-Path Network Reconstruction for Dynamic Inference with Reduced Active Parameters](https://mlsanity.com/paper/2606.09924/) (2026)

## Abstract (arXiv)

Deep neural networks (DNNs) and decision trees (DTs) are both state-of-the-art classifiers. DNNs perform well due to their representational learning capabilities, while DTs are computationally efficient as they perform inference along one route (root-to-leaf) that is dependent on the input data. In this paper, we present DecisioNet (DN), a binary-tree structured neural network. We propose a systematic way to convert an existing DNN into a DN to create a lightweight version of the original model. DecisioNet takes the best of both worlds - it uses neural modules to perform representational learning and utilizes its tree structure to perform only a portion of the computations. We evaluate various DN architectures, along with their corresponding baseline models on the FashionMNIST, CIFAR10, and CIFAR100 datasets. We show that the DN variants achieve similar accuracy while significantly reducing the computational cost of the original network.