Adaptation of artificial intelligence/machine learning models based on site-specific data

An apparatus for wireless communications, comprising:

• at least one memory;
• and
• at least one processor coupled to the at least one memory and configured to:
• transmit, from the apparatus to a network entity, a request for site-specific data associated with a geographic location and a machine learning model of the apparatus, wherein the machine learning model is trained for beam prediction;
• obtain the site-specific data associated with the geographic location;
• adapt the machine learning model for beam prediction corresponding to the geographic location based on using beam prediction data of the site-specific data as labeled outputs to generate an updated machine learning model for estimating or predicting at least one characteristic associated with wireless communications between the apparatus and the network entity;
• and
• transmit an indication associated with adapting the machine learning model based on the site-specific data.

A method for performing wireless communication at a network entity, the method comprising:

• receiving, from a user equipment (UE), a request for site-specific data associated with a geographic location and a machine learning model of the UE, wherein the machine learning model is trained for beam prediction;
• obtaining the site-specific data associated with the geographic location;
• transmitting, to the UE, the site-specific data;
• and
• receiving, from the UE, an indication associated with adapting the machine learning model for beam prediction corresponding to the geographic at the UE based on using beam prediction data of the site-specific data as labeled outputs to generate an updated machine learning model for estimating or predicting at least one characteristic associated with wireless communications between the network entity and the UE.

An apparatus for wireless communication comprising:

• at least one memory;
• and
• at least one processor coupled to the at least one memory and configured to:
• receive, from a user equipment (UE), a request for site-specific data associated with a geographic location and a machine learning model of the UE, wherein the machine learning model is trained for beam prediction;
• obtain the site-specific data associated with the geographic location;
• transmit, to the UE, the site-specific data;
• and
• receive, from the UE, an indication associated with adapting the machine learning model for beam prediction corresponding to the geographic at the UE based on using beam prediction data of the site-specific data as labeled outputs to generate an updated machine learning model for estimating or predicting at least one characteristic associated with wireless communications between the apparatus and the UE.