Parallel construction of classification trees on a GPU

Abstract

Summary Algorithms for constructing tree‐based classifiers are aimed at building an optimal set of rules implicitly described by some dataset of training samples. As the number of samples and/or attributes in the dataset increases, the required construction time becomes the limiting factor for interactive or even functional use. The problem is emphasized if tree derivation is part of an iterative optimization method, such as boosting. Attempts to parallelize the construction of classification trees have therefore been presented in the past. This paper describes a parallel method for binary classification tree construction implemented on a graphics processing unit (GPU) using compute unified device architecture (CUDA). By employing node‐level, attribute‐level, and split‐level parallelism, the task parallel and data parallel sections of tree induction are mapped to the architecture of a modern GPU. The GPU‐based solution is compared with the sequential and multi‐threaded CPU versions on public access datasets, and it is shown that an order of magnitude acceleration can be achieved on this data‐intensive task using inexpensive commodity hardware. The influence of dataset characteristics on the efficiency of parallel implementation is also analyzed. Copyright © 2015 John Wiley & Sons, Ltd.

Optimization of operational costs of Call centers employing classification techniques

“…This can be used in different tasks such as: classification, regression and other analyses, as they improve forecasting models and can also make combinations between trees (Rokach, 2016). There are several studies on how to make a decision tree such as Luštrek et al (2016), Levatić et al (2017), Strnad and Nerat (2016), among others. A situation can be modeled in order to direct more efficient decisionmaking, where its predictive performance is slightly better than the standard algorithms (González, Herrera and Garcia, 2015).…”

Design Automation and Implementation of Machine Learning Classifier Chips

“…This implementation is done using a one-dimensional grid where each block can produce a dataset to train each tree. Similarly, D. Strnad and A. Nerat [6] presented a GPU-based parallel design for a classification tree. The proposed algorithm has three parallelism levels: 1) node level: to find the best split point for multiple attributes on a node concurrently, 2) attribute level: to find the best attribute for multiple nodes concurrently, and 3) split level to evaluate multiple possible split points.…”

Impulsionando Árvores Extremamente Aleatórias em Paralelo para a Classificação de Dados Textuais

“…Os autores usam OpenCL, por funcionar em diferentes arquiteturas. [Strnad and Nerat 2016] exploram a construção deárvores usando paralelismo em nível de nó, nível de atributo e nível de divisão. A abordagem de [Zhang et al 2017] consiste em usar histogramas dos atributos para encontrar a melhor divisão na GPU, a diferença aquié que asárvores são de regressão com boosting, um tipo de ensemble iterativo (cada novo modelo depende do anterior).…”