A method in a user equipment (605) is disclosed. The method comprises acquiring (704, 708) interference mitigation assistance parameters and granularity parameters, determining (712) one or more interfering cells (610B) for which a first strength measurement should be determined, determining (716) a first strength measurement for each of the determined one or more interfering cells, and ordering (720) the one or more interfering cells. The method further comprises identifying (724) from the ordered one or more interfering cells a first number of interfering cells having the strongest first strength measurements, determining (728) a second strength measurement for each of the identified first number of interfering cells, determining (732) one or more cells of the identified first number of interfering cells for which to perform cancellation of interference, and performing (736) cancellation of interference on the determined one or more cells of the identified first number of interfering cells.

An apparatus for receiving wireless communication at a first UE from a first wireless device may include a memory and at least one processor coupled to the memory. The memory and the at least one processor may be configured to receive a user grouping identifying a second UE that communicates with a second wireless device. The memory and the at least one processor may be further configured to receive a control transmission between the second UE and the second wireless device indicating a modulation and coding scheme (MCS) and allocated resources for the second wireless device. The memory and the at least one processor may be further configured to apply interference cancellation on at least one of a resource element (RE) or a resource block (RB) received from the first wireless device based on the MCS and allocated resources for the second wireless device.

A method and network node for deep learning based user clustering in millimeter wave (mmWave) non-orthogonal multiple access (NOMA) are disclosed. According to one aspect, a method includes determining a minimum number of clusters to be served by the network node subject to a first constraint that limits a total number of WDs in each cluster. The method also includes assigning WDs to each cluster of the minimum number of clusters while or after the minimum number of clusters is determined, the determined minimum number of clusters and WD assignments being for a first spatial distribution of the plurality of WDs.