Personalized federated learning method and system for non-independent and identically distributed data

By deploying personalized modulators on the client side and dynamically adjusting the global model, the model adaptation problem of federated learning in non-IID data scenarios is solved, improving accuracy and privacy protection, and achieving adaptive optimization.

CN121766394BActive Publication Date: 2026-06-23BEIJING LINX SOFTWARE CORP
1 Cites 0 Cited by

Patent Information

Application Number
CN202511886927.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-12-15
Publication Date
2026-06-23
Estimated Expiration
2045-12-15

AI Technical Summary

Technical Problem

Existing federated learning methods struggle to adapt to the local data distribution of various clients in Non-IID data scenarios, leading to reduced model performance. Furthermore, personalized training poses a privacy risk and cannot adapt to dynamically changing data environments.

Method used

By employing a personalized federated learning approach, a personalized modulator is deployed on the client side. Based on a recurrent neural network, the temporal features and task preferences of the local data are learned, and adaptation parameters are dynamically generated to adjust the global model. By combining end-to-end training and loss function optimization, the personalization of the local model and privacy protection are achieved.

Benefits of technology

It improves the model's accuracy and user satisfaction in Non-IID scenarios, enhances privacy protection, achieves adaptive optimization of the model, resolves the contradiction between personalization and collaboration, and adapts to dynamic data environments.

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

Abstract

The application relates to a personalized federated learning method and system for non-independent and identically distributed data, and belongs to the technical field of federated learning. The method solves the problems of insufficient personalized adaptation and high privacy leakage risk in the existing non-independent and identically distributed data scene. The method comprises the following steps: a server sends global model parameters to each client; each client trains a local main model based on local data and the received global model parameters, obtains a local parameter increment, and uploads the local parameter increment to the server; time sequence data features are extracted from the local data, and the time sequence data features are transmitted into a trained personalized modulator together with task preference labels to generate local adaptation parameters; the local adaptation parameters are used to adjust the global model parameters to generate a local personalized model for local reasoning; the server receives the local parameter increments of each client, aggregates the local parameter increments to update the global model parameters, and enters the next round of iteration until the iteration end condition is met. The precision of the personalized model and the privacy protection degree are improved.
Need to check novelty before this filing date? Find Prior Art