# US 2025/0097119 A1 · Method for performing transfer learning, communication device, processing device, and storage medium

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0097119 A1
- Document ID: US20250097119A1
- Status: Published application
- Kind: A1
- Application number: 18/726,926
- Filed: 2022-01-06
- Published: 2025-03-20
- Earliest claimed: 2022-01-06
- Assignees: LG Electronics Inc.
- Applicants: LG Electronics Inc.
- Inventors: Yeongjun KIM; Sangrim LEE; Bonghoe KIM; Kyungho LEE
- Web page: https://patentgrep.com/patent/US20250097119A1

## CPC

- H04L 41/16: using machine learning or artificial intelligence
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/08: Learning methods
- H04W 24/02: Arrangements for optimising operational condition
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

The communication device can perform hierarchical transfer learning (TL). The communication device may comprise: receiving information about channel characteristics from a plurality of user equipments including a first user equipment; mapping the plurality of user equipments to a plurality of TL levels and a plurality of groups for each of the plurality of TL levels on the basis of the information about the channel characteristics; and training a neural network of the first user equipment on the basis of the TL levels and the groups to which the plurality of user equipments is mapped. Training of the neural network of the first user equipment can comprise training a training portion for a first TL level from among TL levels to which the first user equipment is mapped.

## Claims

### Claim 1

A method of performing transfer learning (TL) by a communication device in a wireless communication system, the method comprising:
receiving information regarding channel characteristics from a plurality of user equipments (UEs) including a first UE;
mapping the plurality of UEs to a plurality of TL levels and a plurality of groups for each of the plurality of TL levels based on the information regarding the channel characteristics; and
training a neural network of the first UE based on the TL levels and groups to which the plurality of UEs are mapped,
wherein training the neural network of the first UE comprises training a training part for a first TL level among TL levels to which the first UE is mapped.

### Claim 2 (depends on 1)

The method of claim 1, wherein training the training part for the first TL level among the TL levels to which the first UE is mapped comprises:
generating first transfer information based on learning results received from other UEs belonging to a first TL level group to which the first UE is mapped among groups of the first TL level; and
transferring the first transfer information to the first UE.

### Claim 3 (depends on 2)

The method of claim 2, wherein training the neural network of the first UE comprises:
training a training part for a second TL level among the TL levels to which the first UE is mapped, wherein the second TL level is different from the first TL level;
generating second transfer information based on learning results received from other UEs belonging to a second TL level group to which the first UE is mapped among groups of the second TL level; and
transferring the second transfer information to the first UE,
wherein the groups of the second TL level are included in one of the groups of the first TL level.

### Claim 4 (depends on 2)

The method of claim 2, wherein the first transfer information includes parameters and weights of a neural network trained by the other UEs belonging to the first TL level group.

### Claim 5

A communication device configured to perform transfer learning (TL) in a wireless communication system, the communication device comprising:
at least one transceiver;
at least one processor; and
at least one computer memory operably connected to the at least one processor and configured to store instructions that, when executed, cause the at least one processor to perform operations comprising:
receiving information regarding channel characteristics from a plurality of user equipments (UEs) including a first UE;
mapping the plurality of UEs to a plurality of TL levels and a plurality of groups for each of the plurality of TL levels based on the information regarding the channel characteristics; and
training a neural network of the first UE based on the TL levels and groups to which the plurality of UEs are mapped,
wherein training the neural network of the first UE comprises training a training part for a first TL level among TL levels to which the first UE is mapped.

### Claim 6

(canceled)

### Claim 7

A computer-readable storage medium configured to store at least one program code comprising instructions that, when executed, cause at least one processor to perform operations comprising:
receiving information regarding channel characteristics from a plurality of user equipments (UEs) including a first UE;
mapping the plurality of UEs to a plurality of transfer learning (TL) levels and a plurality of groups for each of the plurality of TL levels based on the information regarding the channel characteristics; and
training a neural network of the first UE based on the TL levels and groups to which the plurality of UEs are mapped,
wherein training the neural network of the first UE comprises training a training part for a first TL level among TL levels to which the first UE is mapped.
