Distributed decision tree training

Abstract

A computerized decision tree training system may include a distributed control processing unit configured to receive input of training data for training a decision tree. The system may further include a plurality of data batch processing units, each data batch processing unit being configured to evaluate each of a plurality of split functions of a decision tree for respective data batch of the training data, to thereby compute a partial histogram for each split function, for each datum in the data batch. The system may further include a plurality of node batch processing units configured to aggregate the associated partial histograms for each split function to form an aggregated histogram for each split function for each of a subset of frontier tree nodes and to determine a selected split function for each frontier tree node by computing the split function that produces highest information gain for the frontier tree node.

Description

technical field [0001] The invention relates to the computer field, in particular to decision tree training in the computer field. Background technique [0002] Machine learning techniques can be employed to enable computers to process experimental data and draw conclusions about it. One example machine learning technique is to train a decision tree based on example data, and apply the trained decision tree to classify unknown data into one of several classes. In many applications, using the largest possible dataset for training a decision tree can yield more accurate results. However, one disadvantage of decision tree training using large data sets is that such training can overwhelm the processor or memory resources of a computing system, rendering the training of decision trees impractical or impossible. Consequently, computer scientists and software developers are limited by the size and complexity of the datasets they can use to train decision trees, and it is difficu...

AI Technical Summary

Problems solved by technology

However, one disadvantage of decision tree training using large data sets is that such training can overwhelm the computing system's processor or memory resources, making training of decision trees impractical or impossible

As a result, computer scientists and software developers are limited by the size and complexity of the datasets they can use to train decision trees, and it is difficult to achieve improvements in the classification capabilities of such decision trees

Images