Decision Tree-Based Federated Learning: A Survey
Zijun Wang, Keke Gai
Abstract
Federated learning (FL) has garnered significant attention as a novel machine learning technique that enables collaborative training among multiple parties without exposing raw local data. In comparison to traditional neural networks or linear models, decision tree models offer higher simplicity and interpretability. The integration of FL technology with decision tree models holds immense potential for performance enhancement and privacy improvement. One current challenge is to identify methods for training and prediction of decision tree models in the FL environment. This survey addresses this issue and examines recent efforts to integrate federated learning and decision tree technologies. We review research outcomes achieved in federated decision trees and emphasize that data security and communication efficiency are crucial focal points for FL. The survey discusses key findings related to data privacy and security issues, as well as communication efficiency problems in federated decision tree models. The primary research outcomes of this paper aim to provide theoretical support for the engineering of federated learning with decision trees as the underlying training model.