A UE may identify a plurality of local model update elements associated with an updated local machine learning model. The updated local machine learning model may have been generated based on a global machine learning model received from a base station and a local dataset. The UE may identify one or more local model update elements of the plurality of local model update elements for update element dropping based on at least one of a channel gain, a PAPR specification, an RF emission specification, or an RF condition. The UE may transmit, to the base station over a multiple access channel via analog signaling, at least some local model update elements of the plurality of local model update elements based on dropping of the identified one or more local model update elements.

A UE may identify a plurality of local model update elements associated with an updated local machine learning model. The updated local machine learning model may have been generated based on a global machine learning model received from a base station and a local dataset. The UE may identify one or more local model update elements of the plurality of local model update elements for update element dropping based on at least one of a channel gain, a PAPR specification, an RF emission specification, or an RF condition. The UE may transmit, to the base station over a multiple access channel via analog signaling, at least some local model update elements of the plurality of local model update elements based on dropping of the identified one or more local model update elements.

According to a communication method of the present disclosure, a responder, after the end of transmission sector sweep (TXSS), receives from an initiator a first feedback frame including a BF training type FIELD indicating whether or not to implement a beam forming training (BFT) of a single user multi-input multi-output (SU-MIMO). If the BF training type FIELD indicates that a BFT of the SU-MIMO is to be implemented, the responder transmits to the initiator a second feedback frame based on the result of the TXSS and including a signal to noise ratio (SNR) and a sector identifier (ID) order. The initiator implements the BFT of the SU-MIMO between the initiator and the responder on the basis of the SNR and the sector ID order.

According to a communication method of the present disclosure, a responder, after the end of transmission sector sweep (TXSS), receives from an initiator a first feedback frame including a BF training type FIELD indicating whether or not to implement a beam forming training (BFT) of a single user multi-input multi-output (SU-MIMO). If the BF training type FIELD indicates that a BFT of the SU-MIMO is to be implemented, the responder transmits to the initiator a second feedback frame based on the result of the TXSS and including a signal to noise ratio (SNR) and a sector identifier (ID) order. The initiator implements the BFT of the SU-MIMO between the initiator and the responder on the basis of the SNR and the sector ID order.

According to one or more embodiments, a network node configured to communicate with a wireless device is provided. The network node includes processing circuitry configured to: receive multilayer feedback; determine a beamformer for transmission of a first quantity of transmission layers where the beamformer is based at least on information, in the multilayer feedback, that is associated with a second quantity of transmission layers, where the first quantity of transmission layers is a less than the second quantity of transmission layers; and cause the transmission using the beamformer.

According to one or more embodiments, a network node configured to communicate with a wireless device is provided. The network node includes processing circuitry configured to: receive multilayer feedback; determine a beamformer for transmission of a first quantity of transmission layers where the beamformer is based at least on information, in the multilayer feedback, that is associated with a second quantity of transmission layers, where the first quantity of transmission layers is a less than the second quantity of transmission layers; and cause the transmission using the beamformer.

Methods are disclosed for improving communications on feedback transmission channels, in which there is a possibility of bit errors. The basic solutions to counter those errors are: proper design of the CSI vector quantizer indexing (i.e., the bit representation of centroid indices) in order to minimize impact of index errors, use of error detection techniques to expurgate the erroneous indices and use of other methods to recover correct indices.

Methods are disclosed for improving communications on feedback transmission channels, in which there is a possibility of bit errors. The basic solutions to counter those errors are: proper design of the CSI vector quantizer indexing (i.e., the bit representation of centroid indices) in order to minimize impact of index errors, use of error detection techniques to expurgate the erroneous indices and use of other methods to recover correct indices.

Frequency-selective single frequency network (SFN) operation is disclosed based on a modified Type-II port selection codebook. Within the channel state information (CSI) feedback procedure, a user equipment (UE) observing the CSI-reference signal (CSI-RS) resource configured by the serving base station with two ports configured over multiple sectors of the serving base station may select a precoder from the Type-II port selection codebook which accommodates additional subband amplitude information. The additional subband amplitude information may include a subband dynamic SFN activation indicator. In such a CSI report selected from the Type-II port selection codebook, the UE may indicate to the serving base station both a wideband SFN activation/deactivation and a subband SFN activation/deactivation in addition to the subband phase information. The serving base station may then use this CSI report to activate/deactivate SFN operations in both wideband and subband over each of the participating sectors.

Embodiments of the present disclosure relate to methods and devices for channel state information (CSI) transmission. In example embodiments, a method implemented in a terminal device includes performing a channel estimate between the terminal device and a network device across a predetermined frequency range for a set of beams having different spatial directions; determining, based on the channel estimate, first indication information indicating at least one beam selected from the set of beams and second indication information indicating frequency-related information for the at least one selected beam at a plurality of frequency locations in the predetermined frequency range; and transmitting to the network device the first indication information in a first part of a channel state information (CSI) report and the second indication information in a second part of the CSI report.