Method for performing federated learning in wireless communication system, and apparatus therefor

Patent metadata

Field	Value
Publication number	US-2025023609-A1
Application number	US-202218711460-A
Country	US
Kind code	A1
Filing date	Nov 7, 2022
Priority date	Nov 25, 2021
Publication date	Jan 16, 2025
Grant date	—

Abstract

The present specification provides a method by which a terminal performs federated learning with a plurality of terminals in a wireless communication system. More specifically, the method performed by one terminal comprises the steps of: receiving, from a server, a channel state information reference signal (CSI-RS); transmitting, to the server, channel state information (CSI) calculated on the basis of the CSI-RS; receiving, from the server, (i) information about a global parameter for the federated learning and (ii) compression state information for determining a weight compression method of the one terminal on the basis of channel state information of each of channels between the server and the plurality of terminals; determining a weight compression scheme based on (i) a difference value between the global parameter and a global parameter received before receiving the global parameter and (ii) the compression state information; and transmitting, to the server, an updated local parameter on the basis of the determined weight compression scheme.

First claim

1 . A method for a plurality of user equipments (UEs) to perform a federated learning in a wireless communication system, the method performed by one UE of the plurality of UEs comprising:
receiving, from a server, a channel state information reference signal (CSI-RS); transmitting, to the server, channel state information (CSI) calculated based on the CSI-RS; receiving, from the server, scheduling information that allows the one UE to participate in the federated learning, wherein the scheduling information is constructed based on a reference channel state configured based on channel state information of each of channels between the server and the plurality of UEs; encoding a local parameter for performing the federated learning, the encoded local parameter including a systematic part and a parity part; modulating the encoded local parameter, wherein the parity part is modulated based on a number of retransmissions determined based on (i) a modulation order of the systematic part and the parity part and (ii) a maximum number of UEs participating in the federated learning; and transmitting, to the server, the modulated local parameter based on the scheduling information and the number of retransmissions, wherein a transmission power for the local parameter is controlled based on a difference between a channel state of a channel between the one UE and the server and the reference channel state.

2 . The method of claim 1 , wherein the scheduling information is used to determine whether the one UE participates in the federated learning.

3 . The method of claim 2 , wherein the reference channel state is a channel state between the server and a UE that allows a channel gain between the server and the UE to be highest among the plurality of UEs.

4 . The method of claim 3 , wherein whether the one UE participates in the federated learning is determined based on whether a ratio of a channel gain of a channel between the one UE and the server to a channel gain of the reference channel state is equal to or greater than a specific threshold.

5 . The method of claim 4 , wherein, based on the ratio of the channel gain of the channel between the one UE and the server to the channel gain of the reference channel state being less than the specific threshold, the one UE does not participate in the federated learning.

6 . The method of claim 5 , wherein, based on the ratio of the channel gain of the channel between the one UE and the server to the channel gain of the reference channel state being equal to or greater than the specific threshold, the one UE participates in the federated learning.

7 . The method of claim 1 , wherein the number of retransmissions (i) is greater than or equal to 1 and (ii) is determined to be equal to or less than a value by dividing the maximum number of UEs participating in the federated learning by 2 and rounding up.

8 . The method of claim 1 , wherein, based on a channel gain of the one UE being lowest among respective channel gains of the plurality of UEs participating in the federated learning, an allocation power of the one UE for transmitting the systematic part is set to a maximum power.

9 . The method of claim 8 , wherein, based on the channel gain of the one UE being greater than a lowest channel gain among the respective channel gains of the plurality of UEs participating in the federated learning, the allocation power of the one UE for transmitting the systematic part is set to a value by multiplying a value, that is determined based on a ratio of a channel gain of the one UE to a channel gain of the reference channel state, by the maximum power.

10 . The method of claim 1 , wherein the parity part is divided and transmitted on time/frequency resources as many as the number of retransmissions.

11 . A user equipment (UE) performing a federated learning with a plurality of UEs in a wireless communication system, the UE comprising:
a transmitter configured to transmit a radio signal; a receiver configured to receive the radio signal; at least one processor; and at least one computer memory operably connectable to the at least one processor, wherein the at least one computer memory is configured to store instructions performing operations based on being executed by the at least one processor, wherein the operations comprise: receiving, from a server, a channel state information reference signal (CSI-RS); transmitting, to the server, channel state information (CSI) calculated based on the CSI-RS; receiving, from the server, scheduling information that allows the UE to participate in the federated learning, wherein the scheduling information is constructed based on a reference channel state configured based on channel state information of each of channels between the server and the plurality of UEs; encoding a local parameter for performing the federated learning, the encoded local parameter including a systematic part and a parity part; modulating the encoded local parameter, wherein the parity part is modulated based on a number of retransmissions determined based on (i) a modulation order of the systematic part and the parity part and (ii) a number of the plurality of UEs participating in the federated learning; and transmitting, to the server, the modulated local parameter based on the scheduling information and the number of retransmissions, wherein a transmission power for the local parameter is controlled based on a difference between a channel state of a channel between the UE and the server and the reference channel state.

12 . A method for a base station to perform a federated learning with a plurality of user equipments (UEs) in a wireless communication system, the method comprising:
transmitting, to each of the plurality of UEs, a channel state information reference signal (CSI-RS); receiving, from each of the plurality of UEs, channel state information (CSI) calculated based on the CSI-RS; transmitting, to each of the plurality of UEs, scheduling information that allows the plurality of UEs to participate in the federated learning, wherein the scheduling information is constructed based on a reference channel state configured based on channel state information of each of channels between the server and the plurality of UEs; and receiving, from each of the plurality of UEs, a local parameter for performing the federated learning of each of the plurality of UEs, the local parameter being encoded and modulated by each of the plurality of UEs, wherein the encoded local parameter includes a systematic part and a parity part, wherein the parity part is modulated based on a number of retransmissions determined based on (i) a modulation order of the systematic part and the parity part and (ii) a number of the plurality of UEs participating in the federated learning, wherein the local parameter of each of the plurality of UEs is transmitted based on the scheduling information and the number of retransmissions, wherein a transmission power for the local parameter is controlled based on a difference between a channel state of the channels between the plurality of UEs and the server and the reference channel state.

13 - 15 . (canceled)

Assignees

• Lg Electronics Inc

Inventors

• Jeon Kijun
• Lee Sangrim
• Jung Ikjoo
• Lee Hojae
• Lee Taehyun

Classifications

• H04L41/16

  using machine learning or artificial intelligence · CPC title

• H04L5/0005

  Time-frequency · CPC title

• H04B7/0626 Primary

  Channel coefficients, e.g. channel state information [CSI] · CPC title

• H04W52/367 Primary

  Power values between minimum and maximum limits, e.g. dynamic range · CPC title

• H04L1/00

  Arrangements for detecting or preventing errors in the information received {(correcting synchronisation H04L7/00)} · CPC title