Qualcomm Incorporated

Hamed Pezeshki

Tao Luo

Yan Zhou

Sony Akkarakaran

Taesang Yoo

Arumugam Chendamarai Kannan

Mahmoud Taherzadeh Boroujeni

Xiaoxia Zhang

Konstantinos Dimou

Mostafa Khoshnevisan

Jingchao Bao

Seyed Ali Akbar Fakoorian

Junyi Li

Kazuki Takeda

Eren Balevi

Ajay Gupta

Juan Montojo

Wooseok Nam

Rajat Prakash

Srinivas Yerramalli

Vinod Viswanatha Menon

Jing X Sun

Xiao Feng Wang

Hua Wang

Aziz Gholmieh

Qiang Wu

Vinay Joseph

Seyedkianoush Hosseini

Jung Ho Ryu

Mohamed Fouad Ahmed Marzban

Philip Aaron Sisk

Peter S Gaal

Jelena Damnjanovic

Tianyang Bai

Kiran Venugopal

Vinay Chande

Yong Li

Ruhua He

Lei Xiao

Mohamed Marzban

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.

Gradient dropping for federated learning

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may measure one or more linear combinations, of a set of beams, from a radio access network (RAN) node. Accordingly, the UE may transmit a report, based at least in part on measuring the one or more linear combinations, to the RAN node. The one or more linear combinations may be indicated in one or more rules stored in a memory of the UE or may be indicated in a system information block or a radio resource configuration message. Numerous other aspects are described.

Measurements of linear combinations of beams

Methods, systems, and devices for wireless communications are described. A user equipment (UE) may communicate with multiple transmission reception points (TRPs). The UE may receive control signaling indicating a reference signal configuration. The reference signal configuration, the control signaling, or both may indicate one or more beam failure detection (BFD) reference signals and a quasi co-location (QCL) type associated with a set of BFD reference signal sets. Each BFD reference signal set of the set of BFD reference signal sets may be associated with a respective TRP. The UE may detect a beam failure based on receiving a BFD reference signal set using one or more beams according to the QCL type associated with the BFD reference signal set. The UE may initiate a beam failure recovery procedure based on detecting the beam failure.

Techniques for beam failure detection reference signals

Methods, systems, and devices for wireless communications are described. A user equipment (UE) may be configured to receive control signaling indicating a beam update configuration that defines a timing for updating a common beam for communications with the UE in relation to a communication and in response to a downlink control information (DCI) message that schedules the communication and indicates an update to the common beam. In some aspects, the common beam is shared across a set of channels, a set of reference signals, or both. The UE may then receive, from a base station, the DCI message that schedules the communication and indicates the update to the common beam. The UE may then perform at least one beam switching procedure to update the common beam at the UE based on receiving the DCI message and in accordance with the beam update configuration.

Techniques for common beam update rules for scheduled communications

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may determine that a failure event for a beam or a link, between the UE and a base station, is occurring or will occur, and transmit a message to the base station indicating that the UE is refraining from performing a recovery procedure for the beam or a link for a time duration. Numerous other aspects are provided.

Suspension of beam or link recovery for a failure event

Methods, systems, and devices for wireless communications are described. A user equipment (UE) may receive control signaling from a network node indicating a reference signal (RS) configuration for RS measurements. The RS configuration may indicate a first set of beams, a first periodicity for measuring RSs on the first set of beams, a second set of beams, and a second periodicity for measuring RSs on the second set of beams. The UE may monitor a wireless channel for a first set of RSs communicated via the first set of beams according to the first periodicity and monitor the wireless channel for a second set of RSs communicated via the second set of beams according to the second periodicity. The UE and the network node may dynamically update one or more of the beam sets, periodicities, or both, to perform RS measurements.

Reference signal periodicities for multiple sets of beams

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may determine an update resolution associated with providing, to a base station during a federated learning procedure, an update associated with a machine learning component. The UE may transmit the update to the base station based at least in part on the update resolution. Numerous other aspects are provided.

Update resolution signaling in federated learning

In one aspect, a method of wireless communication includes receiving, by a mobile communication device during a first cycle, a periodic grant via a first carrier of a plurality of carriers, monitoring, by the mobile communication device during a next cycle after the first cycle, for configured grants (CGs) for multiple carriers of the plurality of carriers based on the periodic grant, and receiving, by the mobile communication device during the next cycle after the first cycle, a first transmission in a first CG of the CGs via a second carrier of the plurality of carriers and a second transmission in a second CG of the CGs via a third carrier of the plurality of carriers. Other aspects and features are also claimed and described.

Cross carrier activation of a periodic grant

Aspects relate to wireless communication on multiple component carriers. In some examples, a user equipment (UE) may selectively apply transmission configuration indicator (TCI) information and/or spatial relation information received via a medium access control-control element (MAC-CE) to component carriers. In some examples, a UE may apply the TCI information and/or spatial relation information included in a MAC-CE to multiple component carriers if the UE has been configured with a list that includes the component carriers (and, optionally, if a component carrier identified by the MAC-CE is a member of the list of component carriers). If the above condition is (or conditions are) not met, the UE applies the TCI information and/or spatial relation information included in the MAC-CE to the component carrier identified by the MAC-CE.

Enablement of simultaneous beam update across component carriers

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment may receive, from a base station (BS), a channel state information reference signal (CSI-RS) communication; and transmit, to the BS, a physical uplink control channel communication including feedback information that is a response to the CSI-RS communication and including an interference measurement. Numerous other aspects are provided.

Sub-band interference level indication using physical uplink control channel communication

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive a configuration for a semi-persistent scheduling (SPS) of a data transmission that rate matches the data transmission around one or more resource elements that are to be used for a cell-specific reference signal pattern. The UE may receive an SPS communication based at least in part on the configuration. Numerous other aspects are provided.

Avoiding collisions with reference signals

A method of wireless communication, by a user equipment (UE) includes receiving, from a base station, a jointly trained artificial neural network. The method also includes calculating a value representing at least one of (1) a gradient estimate for a weight of the jointly trained artificial neural network, or (2) the weight of the jointly trained artificial neural network. The method further includes expanding the value into a numerical system with base N into a plurality of digits. The method also includes determining a number and/or a location of the plurality of digits to transmit based on a deterministic task assignment rule received from the base station or a probabilistic task assignment rule. The method further includes transmitting the determined number and/or the determined location of the plurality of digits to the base station.

Federated learning with varying feedback

Methods, systems, and devices for wireless communications are described. A user equipment (UE) may transmit compressed interference information to a network entity. The UE may measure interference at the UE over a set of interference measurement resources. The UE may determine an interference distribution over the set of resources. The UE may encode the interference distribution using a compressions scheme which may reduce a payload or size of the interference distribution. The compression scheme may include compressing the distribution of the interference. Encoding the interference information may include generating a mean vector and a covariance matrix representative of the distribution of the interference measured over the given set of interference measurement resources. The UE may transmit the encoded interference information, and the network entity may decode the encoded interference information. The network entity may schedule communications with the UE based on the interference information.

Interference distribution compression and reconstruction

Certain aspects of the present disclosure are generally directed to a method for wireless communication. The method generally includes determining whether to activate resources on one or more candidate component carriers (CCs) to be used for communication of one or more reference signals with a network based on a signal quality of a serving CC, communicating the one or more reference signals with the network if the resources on the one or more candidate CCs are activated based on the determination, and receiving a data transmission on one of the one or more candidate CCs after the communication of the one or more reference signals.

Dynamically activated channel measurement resources for cross-carrier scheduling

Aspects presented herein may enable a network entity to configure a group of UEs to simultaneously transmit reference signals and to simultaneously transmit gradient vectors to the network entity, such that the network entity may receive the gradient vectors from the group of UEs as an aggregated gradient vector over the air. In one aspect, a base transmits, to a group of UEs, a configuration that configures the group of UEs to simultaneously transmit one or more group-common reference signals and to simultaneously transmit one or more gradient vectors associated with a federated learning procedure. The network entity receives, from the group of UEs, the one or more group-common reference signals and the one or more gradient vectors based on the configuration via multiple channels. The network entity calculates an average gradient vector based on the one or more group-common reference signals and the one or more gradient vectors.

Growing community of inventors

San Diego, CA, United States of America

Hamed Pezeshki