Granted Patent B2

US 12,507,080 · App. 18/091,293 · Granted Dec 23, 2025

Inventors: Mohamed Fouad Ahmed Marzban (San Diego, CA); Wooseok Nam (San Diego, CA); Tao Luo (San Diego, CA); Mahmoud Taherzadeh Boroujeni (San Diego, CA)

Assignee: QUALCOMM Incorporated

H04W16/22G06N20/00

Abstract

Claims (41)

1 . A method for wireless communication at a first user equipment (UE), comprising:

transmitting, from the first UE to a network node, a first message indicating one or more distributions of a group of local data instances stored at the first UE, the group of local data instances associated with a machine learning model implemented at the first UE, each local data instance of the group of local data instances associated with a class of a group of classes;

receiving, associated with transmitting the first message, from the network node, a second message indicating an update to the group of local data instances, in accordance with the one or more distributions of the group of local data instances failing to satisfy one or more data distribution conditions;

updating, at the first UE in accordance with receiving the second message, the group of local data instances in accordance with receiving the first message;

training, at the first UE, the machine learning model with the group of updated local data instances; and

transmitting, from the first UE to the network node, a third message, indicating one or more parameters associated with the machine learning model in accordance with training the machine learning model with the group of updated local data instances.

2 . The method of claim 1 , wherein the one or more data distribution conditions include one or more of a target data distribution, a minimum number of local data instances in each class of the group of classes, a maximum number of local data instances in each class of the group of classes, a ratio between a first number of data instances in one class, of the group of classes, associated with a greatest number of local data instances and a second number of data instances in one class, of the group of classes, associated with a least number of local data instances, a mean value associated with the group of local data instances, or a variance associated with the group of local data instances.

3 . The method of claim 1 , wherein updating the group of local data instances comprises:

augmenting the group of local data instances to include one or more new local data instances such that each distribution of the one or more distributions satisfies the one or more data distribution conditions; and/or

removing one or more local data instances from the group of local data instances such that each distribution of the one or more distributions satisfies the one or more data distribution conditions.

4 . The method of claim 1 , further comprising receiving a fourth message indicating the target data distribution, wherein:

the second message configures the first UE to receive the fourth message.

5 . The method of claim 4 , wherein:

the target data distribution includes indications of one or more target data instances; and

each target data instance of the one or more target data instances is associated with a one class of the group of classes or an input of a group of inputs received at a second UE.

6 . The method of claim 5 , wherein the third message is received via a physical sidelink shared channel (PSSCH) or a physical sidelink control channel (PSCCH).

7 . The method of claim 1 , wherein the update to the group of local data instances indicates an adjustment to an amount of local data instances in the group of local data instances.

8 . The method of claim 1 , wherein the one or more distributions include one of:

a first distribution associated with a set of output data instances associated with outputs from the machine learning model and a second distribution associated with a set of input data instances associated with inputs to the machine learning model; or

the first distribution associated with set of output data instances.

9 . The method of claim 1 , further comprising:

estimating a gradient associated with minimizing a loss function, associated with the machine learning model, based on training the machine learning model,

wherein the gradient is a parameter of the one or more parameters.

10 . A first user equipment (UE) for wireless communications, comprising:

at least one processor; and

at least one memory coupled with the at least one processor and storing instructions operable, when executed by the processor, to cause the apparatus to:

transmit, to a network node, a first message indicating one or more distributions of a group of local data instances stored at the first UE, the group of local data instances associated with a machine learning model implemented at the first UE, each local data instance of the group of local data instances associated with a class of a group of classes;

receive, associated with transmitting the first message, from the network node, a second message indicating an update to the group of local data instances, in accordance with the one or more distributions of the group of local data instances failing to satisfy one or more data distribution conditions;

update, in accordance with receiving the second message, the group of local data instances in accordance with receiving the first message;

train the machine learning model with the group of updated local data instances; and

transmit, to the network node, a third message, indicating one or more parameters associated with the machine learning model in accordance with training the machine learning model with the group of updated local data instances.

11 . The apparatus of claim 10 , wherein the one or more data distribution conditions include one or more of a target data distribution, a minimum number of local data instances in each class of the group of classes, a maximum number of local data instances in each class of the group of classes, a ratio between a first number of data instances in one class, of the group of classes, associated with a greatest number of local data instances and a second number of data instances in one class, of the group of classes, associated with a least number of local data instances, a mean value associated with the group of local data instances, or a variance associated with the group of local data instances.

12 . The apparatus of claim 10 , wherein execution of the instructions to update the group of local data instances further cause the apparatus to:

augment the group of local data instances to include one or more new local data instances such that each distribution of the one or more distributions satisfies the one or more data distribution conditions; and/or

remove one or more local data instances from the group of local data instances such that each distribution of the one or more distributions satisfies the one or more data distribution conditions.

13 . The apparatus of claim 10 , wherein execution of the instructions further cause the apparatus to receive a fourth message indicating a target data distribution, wherein:

the second message configures the first UE to receive the fourth message.

14 . The apparatus of claim 10 , wherein the update to the group of local data instances indicates an adjustment to an amount of local data instances in the group of local data instances.

15 . The apparatus of claim 10 , wherein the one or more distributions include one of:

a first distribution associated with a set of output data instances associated with outputs from the machine learning model and a second distribution associated with a set of input data instances associated with inputs to the machine learning model; or

the first distribution associated with set of output data instances.

Assignments (1)

Continuity (1)

References Cited (19)