Feature selection method and device, equipment and storage medium

Abstract

The invention discloses a feature selection method and device, equipment and a storage medium. The method comprises the steps that any execution node receives an initial selected feature set broadcasted by a management node and feature data corresponding to the initial selected feature set; constructing at least one first candidate feature set; obtaining a model performance index corresponding to the at least one first candidate feature set; in response to the first candidate feature set meeting the selection condition in the at least one first candidate feature set, the first candidate feature set meeting the selection condition is sent to a management node, and the management node is used for obtaining a target selected feature set based on the first candidate feature set meeting the selection condition. In the above process, feature selection can be directly realized based on the stored complete feature data, the selected feature set broadcasted by the management node and the feature data corresponding to the selected feature set, feature data interaction between execution nodes is not needed, the time consumption of the feature selection process is relatively short, the feature selection efficiency is relatively high, and the implementation efficiency is relatively high. And the feature selection effect is relatively good.

Description

technical field [0001] The embodiments of the present application relate to the computer field, and in particular to a feature selection method, device, equipment, and storage medium. Background technique [0002] With the continuous improvement and development of computer storage and computing capabilities, in the field of machine learning, many high-dimensional data sets are often involved. The original feature set corresponding to a high-dimensional data set usually contains a large number of redundant features, and these redundant features will reduce the processing performance of the machine learning model. Feature selection can select the features that work for the machine learning model from the original feature set, and then only use the data set corresponding to the selected features to perform the training or use process of the machine learning model, thereby reducing the computational complexity of the machine learning model and improving the performance of the ma...

AI Technical Summary

Problems solved by technology

The interaction of feature data takes a long time, the efficiency of the feature selection process is low, and the effect of feature selection is not good

Images