Event-triggered activation and deactivation of machine learning functionality

An apparatus for wireless communications at a network entity, comprising:

• a processor;
• memory coupled with the processor;
• and
• instructions stored in the memory and executable by the processor to cause the apparatus to:
• perform wireless communications using a functionality of a machine-learning model used to maintain a wireless communications link with a user equipment (UE);
• determine that the UE has deactivated the functionality of the machine-learning model based at least in part on a triggering event;
• and
• continue to perform wireless communications based at least in part on the determining.

A method for wireless communications at a user equipment (UE), comprising:

• performing wireless communications using a functionality of a machine-learning model used to maintain a wireless communications link;
• detecting a triggering event associated with deactivation of the functionality of the machine-learning model;
• and
• deactivating the functionality of the machine-learning model based at least in part on the detecting.

A method for wireless communications at a network entity, comprising:

• performing wireless communications using a functionality of a machine-learning model used to maintain a wireless communications link with a user equipment (UE);
• determining that the UE has deactivated the functionality of the machine-learning model based at least in part on a triggering event;
• and
• continuing to perform wireless communications based at least in part on the determining.