User equipment-coordination set federated for deep neural networks

A method performed by a user equipment configured as a coordinating user equipment, UE, in a user equipment-coordination set, UECS, of a wireless communication system, for determining at least one common UECS machine-learning, ML, configuration using federated learning, the UECS including at least two UEs configured to at least one of:

• jointly transmit uplink data generated by a target UE of the UECS, or jointly receive downlink data intended for the target UE, the method comprising:
• identifying a subset of UEs, in the UECS to perform peer-to-peer federated learning for one or more DNNs using a training procedure and data local to each UE in the subset of UEs, wherein the one or more DNNs are each configured to perform some or all of a transmitter or a receive processing functionality to process communications at each UE;
• directing each UE in the subset of UEs to perform the peer-to-peer federated learning using a training procedure and data local to each UE in the subset of UEs;
• and
• communicating, to each UE in the subset of UEs, one or more update conditions that indicate when to perform the peer-to-peer federated learning.

A user equipment, UE, comprising:

• a processor;
• and
• computer-readable storage media comprising instructions, responsive to execution by the processor, for directing the user equipment to perform a method for determining a common UECS machine-learning, ML, configuration using federated learning, the UECS including at least two UEs configured to at least one of:
• jointly transmit uplink data generated by a target UE of the UECS, or jointly receive downlink data intended for the target UE, the method comprising:
• communicating, from a coordinating UE to a second UE in the UECS and using one or more side links, one or more update conditions that indicate when to generate updated ML configuration information for one or more deep neural networks, DNNs, that are configured to perform some or all of a transmitter or a receiver processing functionality to process communications at the second UE;
• receiving, from the second UE over the one or more side links, one or more reports, each report including the updated ML configuration information determined by the second UE using a training procedure and input data local to the second UE;
• determining the common UECS ML configuration by applying federated learning techniques to the updated ML configuration information received in the one or more reports;
• and
• directing at least one UE of a subset of UEs to update at least one DNN using the common UECS ML configuration.