A federated learning method, apparatus, device, storage medium, and computer program

By constructing and selecting high-quality decision tree models for fusion in federated learning, the problem of high communication overhead in existing technologies is solved, achieving the effect of reducing communication consumption while protecting data privacy.

CN114282691BActive Publication Date: 2026-05-26TENCENT TECHNOLOGY (SHENZHEN) CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202111264081.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-10-27
Publication Date
2026-05-26
Estimated Expiration
2042-05-26

AI Technical Summary

Technical Problem

Existing federated learning methods fail to effectively reduce communication costs while protecting data privacy, resulting in excessive communication overhead.

Method used

By identifying target features from the data features of the training dataset, constructing candidate decision tree models, and selecting high-quality decision tree models for fusion, the number of model transfers between computing devices is reduced, and model fusion is performed directly on the local machine.

Benefits of technology

While protecting data privacy, it reduces communication overhead, improves the convenience and efficiency of model building, and avoids the communication burden caused by multiple transmissions.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

This application discloses a federated learning method, apparatus, device, storage medium, and computer program, relating to the field of computer technology. The method includes: determining at least one target feature from data features corresponding to a training dataset; using the at least one target feature as the basis for model construction to obtain n candidate decision tree models; determining a target decision tree model from the n candidate decision tree models based on the prediction results of the n candidate decision tree models on training data in the training dataset; sending the target decision tree model to a second computing device, whereby the second computing device fuses at least two decision tree models including the target decision tree model to obtain a federated learning model. Through this method, the first computing device sends a decision tree model to the second computing device in a single transaction while protecting data privacy, making the process of constructing a federated learning model more convenient. This application can be applied to various scenarios such as cloud technology, artificial intelligence, and intelligent transportation.
Need to check novelty before this filing date? Find Prior Art