18563196. METHOD AND DEVICE FOR PERFORMING FEDERATED LEARNING IN WIRELESS COMMUNICATION SYSTEM simplified abstract (LG Electronics Inc.)
Contents
METHOD AND DEVICE FOR PERFORMING FEDERATED LEARNING IN WIRELESS COMMUNICATION SYSTEM
Organization Name
Inventor(s)
METHOD AND DEVICE FOR PERFORMING FEDERATED LEARNING IN WIRELESS COMMUNICATION SYSTEM - A simplified explanation of the abstract
This abstract first appeared for US patent application 18563196 titled 'METHOD AND DEVICE FOR PERFORMING FEDERATED LEARNING IN WIRELESS COMMUNICATION SYSTEM
The present disclosure describes a method for conducting federated learning in a wireless communication system using multiple user equipments (UEs).
- The method involves receiving control information from a base station regarding the scheduling of resources for transmitting local parameters from each UE.
- Each UE transmits a first signal with its local parameter on a first scheduled resource and a second signal on a different scheduled resource, updating a global parameter based on these local parameters.
- The first and second signals are transmitted in a complex conjugate relationship to optimize the learning process.
Potential Applications: - This technology can be applied in 5G and beyond wireless communication systems to improve network efficiency and performance. - It can be used in IoT devices to enable collaborative learning without compromising data privacy.
Problems Solved: - Addresses the challenge of training machine learning models in a distributed manner across multiple UEs in a wireless network. - Enhances the accuracy and speed of federated learning algorithms in a decentralized system.
Benefits: - Improves model accuracy by aggregating local parameters from multiple UEs. - Enhances data privacy and security by keeping sensitive information localized to each UE. - Optimizes network resources by scheduling transmissions efficiently.
Commercial Applications: Title: Enhanced Federated Learning for Wireless Networks This technology can be utilized by telecommunications companies to optimize network performance and offer improved services to customers. It can also be integrated into IoT devices to enhance machine learning capabilities in smart systems.
Questions about Federated Learning in Wireless Communication Systems: 1. How does federated learning benefit from the use of multiple UEs in a wireless network? - Federated learning benefits from multiple UEs by aggregating local parameters to improve model accuracy and efficiency.
2. What are the key challenges in implementing federated learning in wireless communication systems? - The key challenges include optimizing resource scheduling, ensuring data privacy, and maintaining synchronization among UEs.
Original Abstract Submitted
The present disclosure provides a method of performing, by a plurality of user equipments (UEs), a federated learning in a wireless communication system. More specifically, the method performed by one UE of the plurality of UEs comprises receiving, from a base station (BS), control information related to a scheduling of a resource on which the one UE repeatedly transmits a local parameter of the one UE, wherein a global parameter for the federated learning is updated based on respective local parameters of the plurality of UEs: transmitting, to the BS, a first signal including the local parameter of the one UE on a first resource scheduled based on the control information; and transmitting, to the BS, a second signal including the local parameter of the one UE on a second resource that is scheduled based on the control information and is different from the first resource, wherein the first signal and the second signal are transmitted based on the first signal and the second signal being in a complex conjugate relationship.
