Method for collaborative training of ml model based on relay assisted federated learning with over-the-air computation and data privacy

EP4771556A1Pending Publication Date: 2026-07-08TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
0 Cites 0 Cited by

Patent Information

Application Number
EP2023772945
Authority / Receiving Office
EP · EP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-09-01
Publication Date
2026-07-08

AI Technical Summary

Technical Problem

Federated learning in 5G and future cellular communications faces challenges such as data silos, computation capacity, learning accuracy, channel fading, and privacy concerns, particularly in scenarios where explicit data sharing is restricted to preserve confidentiality.

Method used

A method for collaborative training of a machine learning model using relay-assisted federated learning with over-the-air computation and data privacy. This involves a system with user equipment (UEs) that communicate over wireless channels, receive and modify ML model gradients with artificial noise, and transmit these gradients to a relay, which aggregates and further modifies them for privacy before sending to a network node for model updates.

Benefits of technology

The proposed method enhances privacy, improves learning accuracy, and increases the number of UEs that can collaboratively train a model, while also addressing issues of channel fading and communication efficiency through the use of relay-assisted over-the-air computation.

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

Abstract

A method is provided performed by a network node without a direct communication link with a plurality of UEs to collaboratively train a machine learning, ML, model based on a relay assisted distributed ML with over-the-air computation and data privacy. The method includes receiving (506) further modified local ML model gradients from a relay over wireless channels. A further modified local ML model gradient includes a local ML model gradient modified by a respective UE with a first artificial noise for data privacy which is further modified by the relay with a second artificial noise for data privacy. The method further includes aggregating (508) the further modified local ML model gradients based on an over-the-air computation; constructing (510) an updated ML model; and performing (512) one of (i) transmitting the updated ML model to the relay, or (ii) configure variables and start a next round of the collaborative training.
Need to check novelty before this filing date? Find Prior Art