Neural Random Forest Imitation

11/25/2019
by   Christoph Reinders, et al.
1

We present Neural Random Forest Imitation - a novel approach for transforming random forests into neural networks. Existing methods produce very inefficient architectures and do not scale. In this paper, we introduce a new method for generating data from a random forest and learning a neural network that imitates it. Without any additional training data, this transformation creates very efficient neural networks that learn the decision boundaries of a random forest. The generated model is fully differentiable and can be combined with the feature extraction in a single pipeline enabling further end-to-end processing. Experiments on several real-world benchmark datasets demonstrate outstanding performance in terms of scalability, accuracy, and learning with very few training examples. Compared to state-of-the-art mappings, we significantly reduce the network size while achieving the same or even improved accuracy due to better generalization.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/12/2023

Neural Attention Forests: Transformer-Based Forest Improvement

A new approach called NAF (the Neural Attention Forest) for solving regr...
research
02/20/2015

Feature-Budgeted Random Forest

We seek decision rules for prediction-time cost reduction, where complet...
research
08/27/2016

Random Forest for Label Ranking

Label ranking aims to learn a mapping from instances to rankings over a ...
research
06/21/2018

GrCAN: Gradient Boost Convolutional Autoencoder with Neural Decision Forest

Random forest and deep neural network are two schools of effective class...
research
11/18/2019

Neural Forest Learning

We propose Neural Forest Learning (NFL), a novel deep learning based ran...
research
12/13/2014

Oriented Edge Forests for Boundary Detection

We present a simple, efficient model for learning boundary detection bas...
research
11/23/2022

A comparative study of source-finding techniques in HI emission line cubes using SoFiA, MTObjects, and supervised deep learning

The 21 cm spectral line emission of atomic neutral hydrogen (HI) is one ...

Please sign up or login with your details

Forgot password? Click here to reset