Reporting for information aggregation in federated learning
US-2024023091-A1 · Jan 18, 2024 · US
US12568000B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12568000-B2 |
| Application number | US-202118563196-A |
| Country | US |
| Kind code | B2 |
| Filing date | May 21, 2021 |
| Priority date | May 21, 2021 |
| Publication date | Mar 3, 2026 |
| Grant date | Mar 3, 2026 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A method of performing, by a plurality of user equipments (UEs), a federated learning in a wireless communication system comprises receiving, from a base station (BS), control information related to a scheduling of a resource on which the one UE repeatedly transmits a local parameter of the one UE, wherein a global parameter for the federated learning is updated based on respective local parameters of the plurality of UEs; transmitting, to the BS, a first signal including the local parameter on a first resource scheduled based on the control information; and transmitting, to the BS, a second signal including the local parameter on a second resource that is scheduled based on the control information and is different from the first resource, wherein the first signal and the second signal are transmitted based on the first signal and the second signal being in a complex conjugate relationship.
Opening claim text (preview).
The invention claimed is: 1 . A method of performing, by a plurality of user equipments (UEs), a federated learning in a wireless communication system, the method performed by one UE of the plurality of UEs comprising: receiving, from a base station (BS), control information related to a scheduling of a resource on which the one UE repeatedly transmits a local parameter of the one UE, wherein a global parameter for the federated learning is updated based on respective local parameters of the plurality of UEs; transmitting, to the BS, a first signal including the local parameter of the one UE on a first resource scheduled based on the control information; and transmitting, to the BS, a second signal including the local parameter of the one UE on a second resource that is scheduled based on the control information and is different from the first resource, wherein the first signal and the second signal are transmitted based on the first signal and the second signal being in a complex conjugate relationship. 2 . The method of claim 1 , further comprising: before the first signal and the second signal are transmitted, performing a specific operation for removing an impact of a channel on each of the first signal and the second signal. 3 . The method of claim 2 , wherein a method of the specific operation is one of (i) a first method of compensating, based on an amplitude and a phase of an estimated channel for a channel between the one UE and the BS, the channel and (ii) a second method of compensating, based on an average amplitude of estimated channels for channels between the plurality of UEs and the BS and a phase of the estimated channels, the channel. 4 . The method of claim 3 , further comprising: receiving, from the BS, specific operation information for the method of the specific operation. 5 . The method of claim 4 , wherein, based on a ratio of a magnitude of a channel estimation error power, which is a power of channel estimation errors which are errors between channels between the plurality of UEs and the BS and estimated channels for the channels, to a magnitude of a total power of transmission signals of the plurality of UEs, the method of the specific operation represented by the specific operation information is determined as one of the first method and the second method. 6 . The method of claim 5 , wherein, based on the ratio of the magnitude of the channel estimation error power to the magnitude of the total power being equal to or less than a specific value, the specific operation information represents the first method, and wherein, based on the ratio of the magnitude of the channel estimation error power to the magnitude of the total power being greater than the specific value, the specific operation information represents the second method. 7 . The method of claim 6 , further comprising: based on the method of the specific operation represented by the specific operation information being the first method, receiving, from the BS, information on the amplitude and a value of the phase of the estimated channel, wherein, based on the specific operation determined as the first method, the channel between the one UE and the BS is compensated with the amplitude and the value of the phase of the estimated channel included in the information. 8 . The method of claim 6 , further comprising: based on the method of the specific operation represented by the specific operation information being the second method, receiving, from the BS, information on a value of the phase of the estimated channel. 9 . The method of claim 8 , wherein, based on the method of the specific operation represented by the specific operation information being the second method, an amplitude of the channel between the one UE and the BS is compensated at the one UE or the BS. 10 . The method of claim 9 , further comprising: based on the amplitude of the channel being compensated at the one UE, receiving, from the BS, information on a value of the average amplitude of the estimated channels, wherein, based on the specific operation determined as the second method, the channel between the one UE and the BS is compensated with the average amplitude and a value of the phase of the estimated channels. 11 . The method of claim 10 , wherein the information on the value of the average amplitude of the estimated channels is transmitted in a broadcast scheme. 12 . The method of claim 6 , further comprising: based on the first signal and the second signal being transmitted after the one UE receives the specific operation information, determining the method of the specific operation performed on the first signal and the second signal based on the specific operation information, wherein the specific operation is performed on the first signal and the second signal based on the determined method of the specific operation. 13 . The method of claim 4 , further comprising: receiving, from the BS, information representing the method of the specific operation performed by the one UE before the one UE receives the specific operation information, wherein the information represents one of the first method and the second method, and wherein, based on the first signal and the second signal being transmitted before the one UE receives the specific operation information, the specific operation is performed on the first signal and the second signal based on the information. 14 . The method of claim 5 , further comprising: transmitting, to the BS, a reference signal for a channel estimation of the BS for a specific channel on which a signal of the one UE is transmitted; and receiving, from the BS, channel information based on a result of the channel estimation of the BS based on the reference signal, wherein the channel estimation error power is determined based on the channel information. 15 . The method of claim 1 , further comprising: receiving, from the BS, a downlink signal including the updated global parameter. 16 . One user equipment (UE) of a plurality of UEs performing a federated learning in a wireless communication system, the one UE comprising: a transmitter configured to transmit a radio signal; a receiver configured to receive the radio signal; at least one processor; and at least one computer memory operably connectable to the at least one processor, wherein the at least one computer memory is configured to store instructions that allow the at least one processor to perform operations based on being executed by the at least one processor, wherein the operations comprise: receiving, from a base station (BS), control information related to a scheduling of a resource on which the one UE repeatedly transmits a local parameter of the one UE, wherein a global parameter for the federated learning is updated based on respective local parameters of the plurality of UEs; transmitting, to the BS, a first signal including the local parameter of the one UE on a first resource scheduled based on the control information; and transmitting, to the BS, a second signal including the local parameter of the one UE on a second resource that is scheduled based on the control information and is different from the first resource, wherein the first signal and the second signal are transmitted based on the first signal and the second signal being in a complex conjugate relationship. 17 . A method of performing, by a base station (BS), a federated learning together with a plurality of user equipments (UEs) in a wireless communication system, the method comprisin
of multiple channels · CPC title
in the downlink direction of a wireless link, i.e. towards a terminal · CPC title
Distributed learning, e.g. federated learning · CPC title
Supervised learning · CPC title
Convolutional networks [CNN, ConvNet] · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.