Gradient accumulation for federated learning

    公开(公告)号:US12035286B2

    公开(公告)日:2024-07-09

    申请号:US17648117

    申请日:2022-01-14

    CPC classification number: H04W72/044 G06N20/00 H04W24/02

    Abstract: A UE may identify, in each round other than an initial round, a first plurality of local model update elements of a present round. The first plurality of local model update elements of the present round may be associated with an updated local machine learning model. The UE may transmit to a base station, in each round other than the initial round, over a multiple access channel via analog signaling, a second plurality of local model update elements of the present round based on a third plurality of local model update elements of the present round. The third plurality of local model update elements of the present round may correspond to a sum of the first plurality of local model update elements of the present round and a local model update error of a previous round immediately before the present round. The analog signaling may be associated with OTA aggregation.

    Modification of SSB burst pattern
    106.
    发明授权

    公开(公告)号:US12021598B2

    公开(公告)日:2024-06-25

    申请号:US17238122

    申请日:2021-04-22

    CPC classification number: H04B7/088 G06N20/00 H04W16/28 H04W56/001

    Abstract: Certain aspects of the present disclosure provide techniques for efficiently selecting beams for synchronization signal block (SSB) burst transmissions based on a condition. Techniques include selecting certain directions to transmit higher power beams and selecting certain directions to transmit lower power SSB burst transmissions. In some cases, an SSB burst parameter may be modified to use a reduced number of optimal SSB beams. The modified SSB burst parameter may have a reduced SSB burst duration, which may allow for reduced monitoring time by a UE and/or free up resources (that would otherwise be used for SSB transmissions) for data transmissions. Additional aspects relate generally to the beam management procedures in wireless communications systems. Some aspects more specifically relate to the selection of beams for communications to and from a UE and a network entity based on predicted mobility state information for a user equipment (UE).

    User equipment participation indications associated with federated learning

    公开(公告)号:US11956785B2

    公开(公告)日:2024-04-09

    申请号:US17447668

    申请日:2021-09-14

    CPC classification number: H04W72/21 G06N5/022

    Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive, from a base station, a federated learning configuration that configures a participation indication to be used by the UE to indicate a participation status of the UE associated with at least one federated learning round corresponding to a machine learning component. The UE may transmit the participation indication to the base station based at least in part on the federated learning configuration. Numerous other aspects are described.

Patent Agency Ranking