Training Big Random Forests with Little Resources

TL;DR

This paper introduces a resource-efficient framework for training extremely large random forests on commodity hardware by using a multi-level construction scheme that builds and refines trees on data subsets.

Contribution

The paper presents a novel multi-level approach enabling the construction of huge random forests on large datasets with minimal computational resources.

Findings

Efficient training of forests with hundreds of millions of instances.

Demonstrated scalability on dense datasets.

Achieved competitive performance with low-resource setups.

Abstract

Without access to large compute clusters, building random forests on large datasets is still a challenging problem. This is, in particular, the case if fully-grown trees are desired. We propose a simple yet effective framework that allows to efficiently construct ensembles of huge trees for hundreds of millions or even billions of training instances using a cheap desktop computer with commodity hardware. The basic idea is to consider a multi-level construction scheme, which builds top trees for small random subsets of the available data and which subsequently distributes all training instances to the top trees' leaves for further processing. While being conceptually simple, the overall efficiency crucially depends on the particular implementation of the different phases. The practical merits of our approach are demonstrated using dense datasets with hundreds of millions of training instances.