Methods and apparatus for leveraging transfer learning for channel state information enhancement

Patent metadata

Field	Value
Publication number	US-2025350383-A1
Application number	US-202318860105-A
Country	US
Kind code	A1
Filing date	Apr 26, 2023
Priority date	Apr 27, 2022
Publication date	Nov 13, 2025
Grant date	—

Abstract

Methods and apparatus for leveraging transfer learning of one Wireless Transmit/Receive Unit (WTRU) to benefit another WTRU are provided. One method may include the WTRU receiving AI/ML model configuration information indicating one or more AI/ML models available from the network node, a profile associated with the AI/ML models, and a training convergence threshold. Based at least on the profile(s), the WTRU determining that the one or more AI/ML models are not suitable for use by the WTRU, and sending first information indicating that the one or more AI/ML models are not suitable for the WTRU and/or that the WTRU will be training a local AI/ML model. The method may then include training the local AI/ML model according to the convergence threshold, receiving a request to transfer AI/ML model parameters, and sending an indication of the AI/ML model parameters associated with the trained local AI/ML model to the network node.

First claim

1 . A wireless transmit/receive unit (WTRU), comprising:
circuitry, comprising any of a processor, memory, transmitter and receiver, configured to: receive, from a network node, Artificial Intelligence/Machine Learning (AI/ML) model configuration information indicating: one or more AI/ML models available from the network node, one or more profiles associated with the one or more AI/ML models, respectively, and an AI/ML model training convergence threshold, wherein the one or more profiles comprise data distribution statistics and model parameters associated with the one or more AI/ML models; based at least on the one or more profiles, determine that the one or more AI/ML models are not suitable for use by the WTRU; send first information, to the network node, indicating any of: the one or more AI/ML models are not suitable for the WTRU and the WTRU will be training a local AI/ML model; train the local AI/ML model according to the convergence threshold; receive second information indicating a request, from the network node, to transfer AI/ML model parameters; and send third information indicating the AI/ML model parameters associated with the trained local AI/ML model to the network node.

2 . The WTRU of claim 1 , wherein the one or more profiles comprises any of: data distribution statistics and model parameters associated with the AI/ML models, and
wherein the model parameters comprise any of channel measurements associated with the AI/ML models; static information associated with the AI/ML models;
performance information associated with the AI/ML models; and
training frequency associated with the AI/ML models.

3 . (canceled)

4 . The WTRU of claim 1 , wherein the circuitry is configured to determine that the one or more AI/ML models are not suitable based on measured radio conditions and any of: the one or more profiles, configured performance thresholds, and capabilities of the WTRU.

5 . The WTRU of claim 4 , the circuitry configured to:
compare at least one measurement performed by the WTRU with the configured performance thresholds; and based on the comparison, further determine that the one or more AI/ML models are not suitable.

6 . The WTRU of claim 1 , wherein, to train the local AI/ML model according to the convergence threshold, the circuitry is configured to:
determine an error from an output of the local AI/ML model and measured channel conditions; on condition that the error is greater than the convergence threshold, perform additional iterations of the training to achieve convergence of the local AI/ML model; on condition that the error is less than the convergence threshold, report completion of the training of the local AI/ML model to the network node.

7 . The WTRU of claim 1 , wherein the first information comprises an indication of a condition associated with the one or more profiles that was determined by the WTRU to have failed.

8 . The WTRU of claim 7 , wherein the failed condition comprises signal-to-interference plus noise ratio (SINR) measured by the WTRU not being within range of the SINR of any of the AI/ML models available from the network node.

9 . The WTRU of claim 1 , wherein the WTRU is configured to transmit assistance information to the network node, and wherein the assistance information indicates any of: capability information including AI/ML model types that the WTRU is configured with, antenna configuration information for the WTRU, and location information for the WTRU.

10 . (canceled)

11 . The WTRU of claim 1 , wherein the configuration information comprises a trigger or command to determine whether the one or more AI/ML models are suitable for use for at least one function at the WTRU.

12 . The WTRU of claim 1 , wherein any of the one or more AI/ML models and the local AI/ML model are configured to perform any of channel state information (CSI) estimation or CSI prediction.

13 . (canceled)

14 . A method, implemented in a wireless transmit/receive unit (WTRU), the method comprising:
receiving, from a network node, AI/ML model configuration information indicating: one or more AI/ML models available from the network node, one or more profiles associated with the one or more AI/ML models, respectively, and an AI/ML model training convergence threshold, wherein the one or more profiles comprise data distribution statistics and model parameters associated with the one or more AI/ML models; based at least on the one or more profiles, determining that the one or more AI/ML models are not suitable for use by the WTRU; sending first information, to the network node, indicating: the one or more AI/ML models are not suitable for the WTRU and the WTRU will be training a local AI/ML model; training the local AI/ML model according to the convergence threshold; receiving second information indicating a request, from the network node, to transfer AI/ML model parameters; and sending third information indicating the AI/ML model parameters associated with the trained local AI/ML model to the network node.

15 . The method of claim 14 , wherein the one or more profiles comprises any of: data distribution statistics and model parameters associated with the AI/ML models, and
wherein the model parameters comprise any of: channel measurements associated with the AI/ML models; static information associated with the AI/ML models;
performance information associated with the AI/ML models; and
training frequency associated with the AI/ML models.

16 . (canceled)

17 . The method of claim 14 , wherein determining that the one or more AI/ML models are not suitable is based on measured radio conditions and any of: the one or more profiles, configured performance thresholds, and capabilities of the WTRU.

18 . The method of claim 17 , comprising:
comparing at least one measurement performed by the WTRU with the configured performance thresholds; and based on the comparison, further determining that the one or more AI/ML models are not suitable.

19 . The method of claim 14 , wherein the training of the local AI/ML model according to the convergence threshold comprises:
determining an error from an output of the local AI/ML model and measured channel conditions; on condition that the error is greater than the convergence threshold, performing additional iterations of the training to achieve convergence of the local AI/ML model; on condition that the error is less than the convergence threshold, reporting completion of the training of the local AI/ML model to the network node.

20 . The method of claim 14 , wherein the first information comprises an indication of a condition associated with the one or more profiles that was determined by the WTRU to have failed.

21 . The method of claim 20 , wherein the failed condition comprises signal-to-interference plus noise ratio (SINR) measured by the WTRU not being within range of the SINR of any of the AI/ML models available from the network node.

22 . The method of claim 14 , comprising transmitting assistance information to the network node, and wherein the assistance information indicates any of: capability information including AI/ML model types that the WTRU is configured with, antenna configuration information for the WTRU, and location information for the WTRU.

23 . (canceled)

24 . The method of claim 14 , wherein the configuration information comprises a trigger or command to determine whether the one or more AI/M

Assignees

• Interdigital Patent Holdings Inc

Inventors

• Lutchoomun Tejaswinee
• Tooher Patrick
• Beluri Mihaela
• Narayanan Thangaraj Yugeswar Deenoo
• Malhotra Akshay
• Lee Moon Il
• Katla Satyanarayana

Classifications

• H04B7/0626 Primary

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

• H04B17/3913

  Predictive models, e.g. based on neural network models · CPC title

• G06N3/096

  Transfer learning · CPC title

• H04B17/373

  Predicting channel quality {or other radio frequency [RF]} parameters · CPC title

• H04B17/336 Primary

  Signal-to-interference ratio [SIR] or carrier-to-interference ratio [CIR] · CPC title