Apparatus and method for monitoring a two-sided model for reporting in a wireless communication system

Abstract

Various aspects of the present disclosure relate to wireless communication. A first apparatus may determine (702) a set of encoder parameters for an encoder model of a two-sided model. The first apparatus may transmit (704) encoded data. The encoded data may be based on an input sample and the encoder model, and the input sample may determine the input to the encoder model and a preferred output of the two-sided model. The first apparatus may also receive (706) a first set of information associated with an output of the two-sided model of a subset of the input sample. The subset of the input sample may be determined based on a first message received from another apparatus or based on a relevance metric determined for each input sample of the input samples. The first apparatus may determine (708) a model metric associated with performance of the two-sided model.

Description

APPARATUS AND METHOD FOR CONFIGURING A TWO-SIDED MODEL OF A WIRELESS COMMUNICATION SYSTEM TECHNICAL FIELD

[0001] The present disclosure relates to wireless communications, and more specifically to configuring a two-sided model of a wireless communication system. BACKGROUND

[0002] A wireless communications system may include one or multiple network communication devices, such as base stations, which may support wireless communications for one or multiple user communication devices, which may be otherwise known as user equipment (UE), or other suitable terminology. The wireless communications system may support wireless communications with one or multiple user communication devices by utilizing resources of the wireless communication system (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers, or the like). Additionally, the wireless communications system may support wireless communications across various radio access technologies including third generation (3G) radio access technology, fourth generation (4G) radio access technology, fifth generation (5G) radio access technology, among other suitable radio access technologies beyond 5G (e.g., sixth generation (6G)). SUMMARY

[0003] An article “a” before an element is unrestricted and understood to refer to “at least one” of those elements or “one or more” of those elements. The terms “a,” “at least one,” “one or more,” and “at least one of one or more” may be interchangeable. As used herein, including in the claims, “or” as used in a list of items (e.g., a list of items prefaced by a phrase such as “at least one of” or “one or more of” or “one or both of”) indicates an inclusive list such that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C). Also, as used herein, the phrase “based on” shall not be construed as a reference to a closed set of conditions. For example, an example step that is described as “based on condition A” may be based on both a condition A and a condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase “based on” shall beconstrued in the same manner as the phrase “based at least in part on.” Further, as used herein, including in the claims, a “set” may include one or more elements.

[0004] Various aspects of the present disclosure relate to wireless communications, including improved methods and apparatuses that support configuring a two-sided model (e.g., encoder and decoder) of a wireless communication system. A first apparatus may determine a set of encoder parameters for an encoder model of a two- sided model and transmit encoded data to a second apparatus. The encoded data may be based on an input sample and the encoder model, and the input sample may determine the input to the encoder model and a preferred output of the two-sided model. The first apparatus may also receive a first set of information associated with an output of the two-sided model of a subset of the input sample. The subset of the input sample may be determined based on a first message received from another apparatus or based on a relevance metric determined for each input sample of the input samples. The first apparatus may determine a model metric associated with performance of the two-sided model. The model metric may be computed based on the input sample and the first set of information. BRIEF DESCRIPTION OF THE DRAWINGS

[0005] Figure 1 illustrates an example of a wireless communications system in accordance with aspects of the present disclosure.

[0006] Figure 2 illustrates an example of a wireless network in accordance with aspects of the present disclosure.

[0007] Figure 3 illustrates an example of a block diagram of a two-sided model in accordance with aspects of the present disclosure.

[0008] Figure 4 illustrates an example of a UE in accordance with aspects of the present disclosure.

[0009] Figure 5 illustrates an example of a processor in accordance with aspects of the present disclosure.

[0010] Figure 6 illustrates an example of a network equipment (NE) in accordance with aspects of the present disclosure.

[0011] Figure 7 illustrates a flowchart of a method performed by a first apparatus in accordance with aspects of the present disclosure.

[0012] Figure 8 illustrates a flowchart of a method performed by a second apparatus in accordance with aspects of the present disclosure.

[0013] Figure 9 illustrates a flowchart of another method performed by a first apparatus in accordance with aspects of the present disclosure.

[0014] Figure 10 illustrates a flowchart of another method performed by a second apparatus in accordance with aspects of the present disclosure. DETAILED DESCRIPTION

[0015] Various aspects of the present disclosure relate to supporting (e.g., configuring, enabling) a two-sided model of a wireless communication system. The two-sided model may be associated with an encoder of a first wireless device (which may be referred to as an encoder device) and a decoder of the first wireless device or a second wireless device (which may be referred to as a decoder device). Some functions (e.g., operations, behaviors, features) of the model may be performed by the first wireless device (e.g., the encoder device) and other functions (e.g., operations, behaviors, features) of the model may be performed by the first wireless device or the second wireless device (e.g., the decoder device). In some implementations, one or more of the first wireless device (e.g., the encoder device) or the second wireless device (e.g., the decoder device) may manage (e.g., update, adjust, modify) a set of one or more parameters of the two-sided model at a corresponding frequency (e.g., rate, pattern, interval). However, in some cases, excessive data may be used, for example, based on a quantity of data transferred to update the two-sided model and a frequency (e.g., rate) of the updates. By reducing one or more of the transfers including the quantity of data for updating the two-sided model or the frequency (e.g., interval) of updating the two-sided, apparatuses (e.g., wireless devices) performing one or more of encoding or decoding may reduce power consumption, reduce processor usage, reduce data usage, and increase overall system performance.

[0016] Aspects of the present disclosure are described in the context of a wireless communications system.

[0017] Figure 1 illustrates an example of a wireless communications system 100 in accordance with aspects of the present disclosure. The wireless communications system 100 may include one or more NE 102, one or more UE 104, and a core network (CN) 106. The wireless communications system 100 may support various radio access technologies. In some implementations, the wireless communications system 100 may be a 4G network, such as an LTE network or an LTE-Advanced (LTE-A) network. In some other implementations, the wireless communications system 100 may be a new radio (NR) network, such as a 5G network, a 5G-Advanced (5G-A) network, or a 5G ultrawideband (5G-UWB) network. In other implementations, the wireless communications system 100 may be a combination of a 4G network and a 5G network, or other suitable radio access technology including Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20. The wireless communications system 100 may support radio access technologies beyond 5G, for example, 6G. Additionally, the wireless communications system 100 may support technologies, such as time division multiple access (TDMA), frequency division multiple access (FDMA), or code division multiple access (CDMA), etc.

[0018] The one or more NE 102 may be dispersed throughout a geographic region to form the wireless communications system 100. One or more of the NE 102 described herein may be or include or may be referred to as a network node, a base station, a network element, a network function, a network entity, a radio access network (RAN), a NodeB, an eNodeB (eNB), a next-generation NodeB (gNB), or other suitable terminology. An NE 102 and a UE 104 may communicate via a communication link, which may be a wireless or wired connection. For example, an NE 102 and a UE 104 may perform wireless communication (e.g., receive signaling, transmit signaling) over a Uu interface.

[0019] An NE 102 may provide a geographic coverage area for which the NE 102 may support services for one or more UEs 104 within the geographic coverage area. For example, an NE 102 and a UE 104 may support wireless communication of signals related to services (e.g., voice, video, packet data, messaging, broadcast, etc.) according to one or multiple radio access technologies. In some implementations, an NE 102 may be moveable, for example, a satellite associated with a NTN. In some implementations, different geographic coverage areas associated with the same or different radio accesstechnologies may overlap, but the different geographic coverage areas may be associated with different NE 102.

[0020] The one or more UE 104 may be dispersed throughout a geographic region of the wireless communications system 100. A UE 104 may include or may be referred to as a remote unit, a mobile device, a wireless device, a remote device, a subscriber device, a transmitter device, a receiver device, or some other suitable terminology. In some implementations, the UE 104 may be referred to as a unit, a station, a terminal, or a client, among other examples. Additionally, or alternatively, the UE 104 may be referred to as an Internet-of-Things (IoT) device, an Internet-of-Everything (IoE) device, or machine-type communication (MTC) device, among other examples.

[0021] A UE 104 may be able to support wireless communication directly with other UEs 104 over a communication link. For example, a UE 104 may support wireless communication directly with another UE 104 over a device-to-device (D2D) communication link. In some implementations, such as vehicle-to-vehicle (V2V) deployments, vehicle-to-everything (V2X) deployments, or cellular-V2X deployments, the communication link may be referred to as a sidelink. For example, a UE 104 may support wireless communication directly with another UE 104 over a UE-to-UE interface (PC5 interface).

[0022] An NE 102 may support communications with the CN 106, or with another NE 102, or both. For example, an NE 102 may interface with other NE 102 or the CN 106 through one or more backhaul links (e.g., S1, N2, N2, or network interface). In some implementations, the NE 102 may communicate with each other directly. In some other implementations, the NE 102 may communicate with each other or indirectly (e.g., via the CN 106. In some implementations, one or more NE 102 may include subcomponents, such as an access network entity, which may be an example of an access node controller (ANC). An ANC may communicate with the one or more UEs 104 through one or more other access network transmission entities, which may be referred to as a radio heads, smart radio heads, or transmission-reception points (TRPs).

[0023] The CN 106 may support user authentication, access authorization, tracking, connectivity, and other access, routing, or mobility functions. The CN 106 may be an evolved packet core (EPC), or a 5G core (5GC), which may include a control plane entity that manages access and mobility (e.g., a mobility management entity (MME), anaccess and mobility management functions (AMF)) and a user plane entity that routes packets or interconnects to external networks (e.g., a serving gateway (S-GW), a Packet Data Network (PDN) gateway (P-GW), or a user plane function (UPF)). In some implementations, the control plane entity may manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management (e.g., data bearers, signal bearers, etc.) for the one or more UEs 104 served by the one or more NE 102 associated with the CN 106.

[0024] The CN 106 may communicate with a packet data network over one or more backhaul links (e.g., via an S1, N2, N2, or another network interface). The packet data network may include an application server. In some implementations, one or more UEs 104 may communicate with the application server. A UE 104 may establish a session (e.g., a protocol data unit (PDU) session, or the like) with the CN 106 via an NE 102. The CN 106 may route traffic (e.g., control information, data, and the like) between the UE 104 and the application server using the established session (e.g., the established PDU session). The PDU session may be an example of a logical connection between the UE 104 and the CN 106 (e.g., one or more network functions of the CN 106).

[0025] In the wireless communications system 100, the NEs 102 and the UEs 104 may use resources of the wireless communications system 100 (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers)) to perform various operations (e.g., wireless communications). In some implementations, the NEs 102 and the UEs 104 may support different resource structures. For example, the NEs 102 and the UEs 104 may support different frame structures. In some implementations, such as in 4G, the NEs 102 and the UEs 104 may support a single frame structure. In some other implementations, such as in 5G and among other suitable radio access technologies, the NEs 102 and the UEs 104 may support various frame structures (i.e., multiple frame structures). The NEs 102 and the UEs 104 may support various frame structures based on one or more numerologies.

[0026] One or more numerologies may be supported in the wireless communications system 100, and a numerology may include a subcarrier spacing and a cyclic prefix. A first numerology (e.g., ^=0) may be associated with a first subcarrier spacing (e.g., 15 kHz) and a normal cyclic prefix. In some implementations, the first numerology (e.g., ^=0) associated with the first subcarrier spacing (e.g., 15 kHz) mayutilize one slot per subframe. A second numerology (e.g., ^=1) may be associated with a second subcarrier spacing (e.g., 30 kHz) and a normal cyclic prefix. A third numerology (e.g., ^=2) may be associated with a third subcarrier spacing (e.g., 60 kHz) and a normal cyclic prefix or an extended cyclic prefix. A fourth numerology (e.g., ^=3) may be associated with a fourth subcarrier spacing (e.g., 120 kHz) and a normal cyclic prefix. A fifth numerology (e.g., ^=4) may be associated with a fifth subcarrier spacing (e.g., 240 kHz) and a normal cyclic prefix.

[0027] A time interval of a resource (e.g., a communication resource) may be organized according to frames (also referred to as radio frames). Each frame may have a duration, for example, a 10 millisecond (ms) duration. In some implementations, each frame may include multiple subframes. For example, each frame may include 10 subframes, and each subframe may have a duration, for example, a 1 ms duration. In some implementations, each frame may have the same duration. In some implementations, each subframe of a frame may have the same duration.

[0028] Additionally or alternatively, a time interval of a resource (e.g., a communication resource) may be organized according to slots. For example, a subframe may include a number (e.g., quantity) of slots. The number of slots in each subframe may also depend on the one or more numerologies supported in the wireless communications system 100. For instance, the first, second, third, fourth, and fifth numerologies (i.e., ^=0, ^=1, ^=2, ^=3, ^=4) associated with respective subcarrier spacings of 15 kHz, 30 kHz, 60 kHz, 120 kHz, and 240 kHz may utilize a single slot per subframe, two slots per subframe, four slots per subframe, eight slots per subframe, and 16 slots per subframe, respectively. Each slot may include a number (e.g., quantity) of symbols (e.g., orthogonal frequency division multiplexing (OFDM) symbols). In some implementations, the number (e.g., quantity) of slots for a subframe may depend on a numerology. For a normal cyclic prefix, a slot may include 14 symbols. For an extended cyclic prefix (e.g., applicable for 60 kHz subcarrier spacing), a slot may include 12 symbols. The relationship between the number of symbols per slot, the number of slots per subframe, and the number of slots per frame for a normal cyclic prefix and an extended cyclic prefix may depend on a numerology. It should be understood that reference to a first numerology (e.g., ^=0) associated with a first subcarrier spacing (e.g., 15 kHz) may be used interchangeably between subframes and slots.

[0029] In the wireless communications system 100, an electromagnetic (EM) spectrum may be split, based on frequency or wavelength, into various classes, frequency bands, frequency channels, etc. By way of example, the wireless communications system 100 may support one or multiple operating frequency bands, such as frequency range designations FR1 (410 MHz – 7.125 GHz), FR2 (24.25 GHz – 52.6 GHz), FR3 (7.125 GHz – 24.25 GHz), FR4 (52.6 GHz – 114.25 GHz), FR4a or FR4-1 (52.6 GHz – 71 GHz), and FR5 (114.25 GHz – 300 GHz). In some implementations, the NEs 102 and the UEs 104 may perform wireless communications over one or more of the operating frequency bands. In some implementations, FR1 may be used by the NEs 102 and the UEs 104, among other equipment or devices for cellular communications traffic (e.g., control information, data). In some implementations, FR2 may be used by the NEs 102 and the UEs 104, among other equipment or devices for short-range, high data rate capabilities.

[0030] FR1 may be associated with one or multiple numerologies (e.g., at least three numerologies). For example, FR1 may be associated with a first numerology (e.g., ^=0), which includes 15 kHz subcarrier spacing; a second numerology (e.g., ^=1), which includes 30 kHz subcarrier spacing; and a third numerology (e.g., ^=2), which includes 60 kHz subcarrier spacing. FR2 may be associated with one or multiple numerologies (e.g., at least 2 numerologies). For example, FR2 may be associated with a third numerology (e.g., ^=2), which includes 60 kHz subcarrier spacing; and a fourth numerology (e.g., ^=3), which includes 120 kHz subcarrier spacing.

[0031] Figure 2 illustrates an example of a wireless network 200 in accordance with aspects of the present disclosure. The wireless network 200 may include a NE 102-a (e.g., one embodiment of a NE 102, a gNB), a first UE 104-a (e.g., one embodiment of a UE 104, UE1), a second UE 104-b (e.g., one embodiment of a UE 104, UE2), and a third UE 104-c (e.g., one embodiment of a UE 104, UEK, the third UE 104-c represents any number of additional UEs).

[0032] Specifically, Figure 2 shows one example of the wireless network 200 with one NE 102-a (e.g., may be represented by node ^^and may be equipped with ^antennas) and ^ UEs 104-a, 104-b, 104-c (e.g., may be denoted by ^^, ^^ , ⋯ , ^^ thateach have ^ antennas). ^^^^^^may denote a channel at time ^frequency band^, ^ ∈ {1,2, … , ^} , between ^^ and ^^ which may form a matrix of size ^ × ^ withcomplex entries, i.e., ^^^ ^^^ ∈ ℂ^×^ .

[0033] At time ^ and frequency band ^, it may be assumed that the NE 102-a wants to transmit message ^^^ ^^^ to user ^^ where = {1,2, ⋯ , ^} while it uses " ^^ ^^^ ∈ℂ^×^as a The received signal at ^^, #^^^^^, may be written as:#^^ ^^^ = ^^^^^^"^^^^^^^^ ^^^ + %^^^^^ where %^^^^^ represents a noise vector at a receiver.

[0034] To improve an achievable rate of the link, in one example, the NE 102-a selects "^^^^^ that maximizes a received signal-to-interference and noise ratio (SINR). Several different configurations may be used for selection of "^^^^^ where some of the configurations may have some knowledge about ^^^^^^.

[0035] The NE 102-a may get knowledge ofby direct measurement (e.g., in a time duplex division (TDD) mode and assuming reciprocity of a channel), or indirectly using information that one of the UEs 104-a, 104-b, and 104-c sends to the NE 102-a (e.g., in a frequency division duplex (FDD) mode). In the indirect method, a large amount of feedback may be used to send accurate information about ^^^^^^. This may require a large amount of data if there are a large number of antennas or / and large frequency bands.

[0036] In one example, a single time slot is analyzed, but the example may be extended to the examples with more than a single time slot. Without loss of generality, ^^^^^^may be denoted using ^^^ . ^^^^^ may be defined as a matrix of size ^ × ^ × ^which is formed by stacking ^^^for all frequency bands (e.g., the entries at^^&', (, ^)^^^ is equal to ^ ^^ &', ()^^^^. Each UE 104-a, 104-b, and 104-c may providefeedback information about most recent ^ × ^ × ^ complex numbers to the Ne 102-a.

[0037] Various configurations may be used to reduce a rate of required feedback. Two-sided methods may include two parts where a first part is deployed at a UE side (e.g., UE 104) and the second part is deployed at a gNB side (e.g., NE 102). The UE and gNB sides may include one or a few neural network (NN) blocks which are trained using data driven approaches. The UE side may be responsible for computing a latent representation of input data (e.g., what needs to be transferred to the gNB) with as lowof a number of bits as possible. Receiving what has been transmitted by the UE side, the gNB side reconstructs the information intended to be transmitted to the gNB.

[0038] Figure 3 illustrates an example of a block diagram of a two-sided model 300 (e.g., NN-based model) in accordance with aspects of the present disclosure. The two- sided model 300 includes a node A 302 (e.g., encoder, encoding model, Me) and a node B 304 (e.g., decoder, decoding model, Md). Figure 3 illustrates only one example of a two-sided model 300, while in other examples the location of the encoder and decoder may be swapped. Input data 306 is provided to the node A 302, then there is a latent representation 308 in communications from the node A 302 to the node B 304, and the node B 304 outputs data 310. In some configurations, the node A 302 is located at the UE 104, and the node B 304 is located at the NE 102, but in other configurations the node A 302 and the node B 304 may be located in other devices.

[0039] The exact structure of a UE and a gNB side may vary depending on a particular scheme, but in some embodiment training of an encoder and decoder are not online, meaning that the encoder and the decoder training is based on some criteria and an NN-block of the encoder and the decoder are fixed during an inference phase.

[0040] Using fixed encoder and decoder blocks, the performance of the two-sided model 300 (e.g., the accuracy of reconstructed output) may be reduced if conditions of an environment change to a state that the two-sided model 300 is not trained for. So, it may be desirable to monitor a performance of the two-side model 300 continuously to detect deviation from a desirable behavior.

[0041] In different configurations, there may be different monitoring schemes. Some of the monitoring schemes may be indirect and based on performance of a subsequent task (e.g., meaning that the output of the decoder is used for a subsequent task, the throughput of a network if a desired precoder is being fed back). If the performance is low, the two-sided model 300 may not be performing correctly. Moreover, performance of a subsequent task might be also affected by factors other than correctness of a model output. So, it may not be accurate to associate a lower performance with a correctness of a model output.

[0042] For the two-sided model 300, one monitoring approach is to compare the output data 310 of the node B 304 with what it should be (e.g., a desired output, apreferred output). For example, if the output data 310 should be ^^&', (, ^), oneexample may have the UE send a correct ^^&', (, ^) to a gNB (e.g., using conventionalfeedback mechanism). Then, the gNB may compare the ^* ^&', (, ^) that it has estimatedusing the two-sided model 300 and the correct ^^&', (, ^) which it has received. If thedifference between them is large, then the gNB may decide that the two-sided model 300 is not well-calibrated and may initiate an update process.

[0043] One configuration may include the node B 304 feeding back what it has estimated to the node A 302. For example, the node A 302 may compare estimated values with preferred values. If the difference in the comparison is larger than a threshold, the UE may decide that the two-sided model 300 is not performing well. To enable such monitoring schemes, one node may need to send side information to another node. More precisely: if monitoring happens at the node B 304, then the node A 302 may send preferred output values in addition to a latent representation to the node B 304, and if the monitoring happens at the node A 302, then the node B 304 may send back model output to the node A 302.

[0044] Extra overhead for sending side information may be a challenge, such as if a system needs to send the side information frequently. Various embodiments found herein include methods to reduce monitoring overhead by reducing a frequency of transmission of side information.

[0045] In one example of a two-sided model 300, ℳ is used to refer to a complete model while ^,and ^- refer to the node A 302 (e.g., UE side) and the node B 304 (e.g., gNB side) of the two-sided model 300. It should be noted that implementations described herein are also applicable to scenarios where the roles of the UE and the gNB are reversed with the two-sided model 300 (e.g., the encoder, ^,model is performed at the gNB and the decoder, ^- model is performed at the UE).

[0046] Moreover, ., / , 01, # are used to denote an input of ^,, an output of ^,, anoutput of ^-, and a preferred output of ^-, respectively. In some configurations, the node A 302 may have access to . and #. In some cases, for example, for feeding back a precoder for channel state information (CSI) feedback, # may be equal to .. For some configurations, to perform a particular task (e.g., monitoring the performance of the two-sided model) the node A 302 and / or the node B 304 may need some side information. For example, for performance monitoring, the side information needed for monitoring may be # in the node B 304 if it is desired to perform monitoring at the nodeB 304, and may be 01in the node A 302 if it is desired to perform monitoring at the node B 304.

[0047] The two-sided model 300 may be trained (e.g., at a gNB, a network node, or a UE). If it is assumed that the node A 302 also has access ^-, the node A 302 side monitoring may be performed without any overhead. However, this might not be that popular as the node B 304 may not be willing to reveal its model to another side. A more common configuration may be that ^- is not available at the node A 302 and ^,is not available at the node B 304.

[0048] In one implementation, model output comparison occurs at the node A 302. If the node A 302 is able to have access to 01, it may constantly monitor the performance of the two-sided model 300. However, in practice, it is not possible to constantly monitor the performance assuming that ^- is not available at the node A 302. If the node A 302 wants to receive 01from the node B 304 for each sample, it may have a large overhead.

[0049] In one example, the node B 304 may work normally (e.g., not send 01to the node A 302) and, in some time-period, the node B 304 may start sending 01to the node A 302 where 01 is the model output that corresponds to / (e.g., the messages it has received during that period). The node A 302 is then able to compare related 01s and #s.

[0050] To reduce overhead, in certain examples, a relevance metric, 78, is determined for each sample where a larger 78shows that knowledge ofinformation (e.g., 019) may be more beneficial for determining how well the model is working. More precisely, there may be the following alternatives.

[0051] 1. The relevance metric calculation may be performed at the node A 302.

[0052] A. The node A 302 and the node B 304 are in a state that they want to exchange side information helping to determine the performance of the model. This process may have been initiated by the node A 302 or the node B 304 or another node.

[0053] B. The node A 302 receives an input data 〈.; , #;〉 and it generates / ; from .;and sends it to the node B 304.

[0054] C. The node A 302 computes a relevance-metric 78for .;, 78that may be computed with different schemes. As some examples, 78may represent: the quality of asample 〈.;, #;〉 ^e.g., how noisy it is), the difference between the input .; and theprevious samples that the node A 302 observed before, the difference between the input / ;and the previous latent samples that the node A 302 observed generated, if the node A 302 has access to a proxy model it can compare the output of the proxy model with #9and use that information for determining 78− the proxy model is a model that represent^- but not necessarily the actual ^-, and the similarity (e.g., the cosine similarity)between the samples (e.g., the node A 302 gives a high relevance-metric to the first sample), then for the second sample the relevance-metric will be small if its similarity with the first sample is large, and the relevance-metric will be large if its similarity with the first sample is small.

[0055] D. If 78is larger than a threshold, the node A 302 may send a request to the node B 304 to send back the resulted 019. The value of the threshold may have been set by the node B 304 or another node.

[0056] E. The node A 302 is then able to check the validity of the model by comparing the set of 019s and their desired values #9s for samples with the side information.

[0057] 2. The relevance metric calculation may be performed at the node B 304.

[0058] A. The node A 302 and the node B 304 may be in the state that they want to exchange side information helping to determine the performance of the model. This process may have been initiated by the node A 302 or the node B 304 or another node.

[0059] B. The node A 302 receives an input data 〈.;, #;〉 and it generates / ; from .;and sends it to the node B 304.

[0060] C. The node B 304 receives / ;and generates 019.

[0061] D. The node B 304 computes a relevance-metric 78for each received sample, 78may be computed with different schemes. As some examples, 78may represent: the different between the output 019and the previous model outputs of the node B 304 previously generated, the decoder model may have been trained such that it generates a confidence score in addition to 019- the node B 304 may then use this confidence score to determine a relevance metric - for example, a lower confidence score corresponds toa higher relevance metric, and the similarity (e.g., the cosine similarity) between the model outputs (e.g., the node B 304 gives a high relevance-metric to the first sample), then for the second sample the relevance-metric will be small if its similarity with 01>is large, and the relevance-metric will be large if its similarity with 01?is small.

[0062] E. If 78is larger than a threshold, the node B 304 may notify the node A 302 that the node B 304 will send back the resulted 019. The value of the threshold may have been set by the node A 302 or another node.

[0063] F. The node A 302 is then able to check the validity of the model by comparing the set of 019s and their desired values #9s for samples with the side information. As may be appreciated different implementations described herein may be combined.

[0064] In another implementation, model output comparison occurs at the node B 304. If the node B 304 is able to have access to # , it may constantly monitor the performance of the two-sided model 300. However, in practice, it is not possible to constantly monitor the performance since if the node B 304 wants to receive # from the node A 302 for each sample it may require a large overhead.

[0065] In one example, the node A 302 may work normally (e.g., only send / , notsending # to the node B 304) and in some time-period may start sending #9to the node B 304 where #;is the preferred model output corresponds to / ;(e.g., the messages the node A 302 send as the latent representation of input sample .;it has received during that period). The node B 304 is then able to compare related 01s and #s.

[0066] To reduce overhead, in certain examples, a relevance metric, 78, is determined for each sample where a larger 78shows that knowledge of side information (e.g., #;) may be more beneficial for determining how well the model is working. More precisely, there may be the following alternatives.

[0067] 1. The relevance metric calculation may be performed at the node A 302.

[0068] A. The node A 302 and the node B 304 are in a state that they want to exchange side information helping to determine the performance of the model. This process may have been initiated by the node A 302 or the node B 304 or another node.

[0069] B. The node A 302 receives an input data 〈.; , #;〉 and it generates / ; from .;.

[0070] C. The node A 302 computes a relevance-metric 78for .;, 78that may be computed with different schemes. As some examples, 78can represent: the quality of asample 〈.;, #;〉 (e.g., how noisy it is), the different between the input .; and the previoussamples that the node A 302 observed before, the different between the input / ;and the previous latent samples that the node A 302 observed generated, if the node A 302 has access to a proxy model it can compare the output of the proxy model with #9and use that information for determining 78– the proxy model is a model that represent ^- but not necessarily the actual ^- , and the similarity (e.g., the cosine similarity) between the samples (e.g., the node A 302 give a high relevance-metric to the first sample), then for the second sample the relevance-metric will be small if its similarity with the first sample is large, and the relevance-metric will be large if its similarity with the first sample is small.

[0071] D. If 78is smaller than a threshold, the node A 302 sends only / ;to the node B 304, and if 78is larger, the node A 302 also sends #9to the node B 304. The value of the threshold may have been set by the node B 304 or another node.

[0072] E. The node B 304 is then able to check the validity of the model by comparing the set of 019s and their desired values #9s for samples with the side information.

[0073] 2. The relevance metric calculation may be performed at the node B 304.

[0074] A. The node A 302 and the node B 304 may be in the state that they want to exchange side information helping to determine the performance of the model. This process may have been initiated by the node A 302 or the node B 304 or another node.

[0075] B. The node A 302 receives an input data 〈.;, #;〉 and it generates / ; from .;and send it to the node B 304.

[0076] C. The node B 304 receives / ;and generates 019.

[0077] D. The node B 304 computes a relevance-metric 78for each received sample, 78may be computed with different schemes. As some examples, 78may represent: the different between the input 019and the previous model outputs of the node B 304 previously generated, the decoder model may have been trained such that it generates a confidence score in addition to 019- the node B 304 may then use this confidence score to determine relevance metric - for example, a lower confidence score corresponds to ahigher relevance metric, and the similarity (e.g., the cosine similarity) between the model outputs (e.g., the node B 304 gives a high relevance-metric to the first sample), then for the second sample the relevance-metric will be small if its similarity with 01>is large, and the relevance-metric will be large if its similarity with 01?is small.

[0078] E. If 78is larger than a threshold, the node B 304 may send a request to the node A 302 that the node B 304 needs side information #;for this sample. The value of the threshold may have been set by the node A 302 or another node.

[0079] F. The node A 302 then sends #;to the node B 304.

[0080] G. The node B 304 is then able to check the validity of the model by comparing the set of 019s and their desired values #9s for samples with the side information. As may be appreciated different implementations described herein may be combined.

[0081] In various implementations, there may be collecting of training samples for a model update.

[0082] In one configuration, computing a relevance-metric may help to determine which samples are more important for updating of the model. It may be important as many of the samples that are observed during an execution and / or inference phase does not high value if it is desired to update the model for new environment statistics.

[0083] Embodiments described herein may be used to determine a relevance-metricfor new samples that the node A 302 receives. Collecting 〈.;, #;〉 samples with a highrelevance-metric (e.g., instead of all samples) may reduce the size of the training data, lower cost for dataset transfer if needed, and may help achieve higher efficiency for updating of the model since there may be a more informative dataset.

[0084] Figure 4 illustrates an example of a UE 400 in accordance with aspects of the present disclosure. The UE 400 may include a processor 402, a memory 404, a controller 406, and a transceiver 408. The processor 402, the memory 404, the controller 406, or the transceiver 408, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.

[0085] The processor 402, the memory 404, the controller 406, or the transceiver 408, or various combinations or components thereof may be implemented in hardware (e.g., circuitry). The hardware may include a processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.

[0086] The processor 402 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, an ASIC, a field programmable gate array (FPGA), or any combination thereof). In some implementations, the processor 402 may be configured to operate the memory 404. In some other implementations, the memory 404 may be integrated into the processor 402. The processor 402 may be configured to execute computer-readable instructions stored in the memory 404 to cause the UE 400 to perform various functions of the present disclosure.

[0087] The memory 404 may include volatile or non-volatile memory. The memory 404 may store computer-readable, computer-executable code including instructions when executed by the processor 402 cause the UE 400 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 404 or another type of memory. Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer.

[0088] In some implementations, the processor 402 and the memory 404 coupled with the processor 402 may be configured to cause the UE 400 to perform one or more of the functions described herein (e.g., executing, by the processor 402, instructions stored in the memory 404). For example, the processor 402 may support wireless communication at the UE 400 in accordance with examples as disclosed herein. For example, the processor 402 coupled with the memory 404 may be configured to cause the UE 400 to determine a set of encoder parameters for an encoder model of a two- sided model and transmit encoded data to a second apparatus. The encoded data may be based on an input sample and the encoder model, and the input sample may determine the input to the encoder model and a preferred output of the two-sided model. The UE400 may also receive a first set of information associated with an output of the two- sided model of a subset of the input sample. The subset of the input sample may be determined based on a first message received from another apparatus or based on a relevance metric determined for each input sample of the input samples. The UE 400 may determine a model metric associated with performance of the two-sided model. The model metric may be computed based on the input sample and the first set of information.

[0089] The controller 406 may manage input and output signals for the UE 400. The controller 406 may also manage peripherals not integrated into the UE 400. In some implementations, the controller 406 may utilize an operating system such as iOS®, ANDROID®, WINDOWS®, or other operating systems. In some implementations, the controller 406 may be implemented as part of the processor 402.

[0090] In some implementations, the UE 400 may include at least one transceiver 408. In some other implementations, the UE 400 may have more than one transceiver 408. The transceiver 408 may represent a wireless transceiver. The transceiver 408 may include one or more receiver chains 410, one or more transmitter chains 412, or a combination thereof.

[0091] A receiver chain 410 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 410 may include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 410 may include at least one amplifier (e.g., a low-noise amplifier (LNA)) configured to amplify the received signal. The receiver chain 410 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 410 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.

[0092] A transmitter chain 412 may be configured to generate and transmit signals (e.g., control information, data, packets). The transmitter chain 412 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM), frequency modulation (FM), or digital modulation schemes like phase-shift keying (PSK) orquadrature amplitude modulation (QAM). The transmitter chain 412 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 412 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.

[0093] Figure 5 illustrates an example of a processor 500 in accordance with aspects of the present disclosure. The processor 500 may be an example of a processor configured to perform various operations in accordance with examples as described herein. The processor 500 may include a controller 502 configured to perform various operations in accordance with examples as described herein. The processor 500 may optionally include at least one memory 504, which may be, for example, an L1 / L2 / L3 cache. Additionally, or alternatively, the processor 500 may optionally include one or more arithmetic-logic units (ALUs) 506. One or more of these components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., buses).

[0094] The processor 500 may be a processor chipset and include a protocol stack (e.g., a software stack) executed by the processor chipset to perform various operations (e.g., receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) in accordance with examples as described herein. The processor chipset may include one or more cores, one or more caches (e.g., memory local to or included in the processor chipset (e.g., the processor 500) or other memory (e.g., random access memory (RAM), read-only memory (ROM), dynamic RAM (DRAM), synchronous dynamic RAM (SDRAM), static RAM (SRAM), ferroelectric RAM (FeRAM), magnetic RAM (MRAM), resistive RAM (RRAM), flash memory, phase change memory (PCM), and others).

[0095] The controller 502 may be configured to manage and coordinate various operations (e.g., signaling, receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) of the processor 500 to cause the processor 500 to support various operations in accordance with examples as described herein. For example, the controller 502 may operate as a control unit of the processor 500, generating control signals that manage the operation of various components of the processor 500. These control signals include enabling ordisabling functional units, selecting data paths, initiating memory access, and coordinating timing of operations.

[0096] The controller 502 may be configured to fetch (e.g., obtain, retrieve, receive) instructions from the memory 504 and determine subsequent instruction(s) to be executed to cause the processor 500 to support various operations in accordance with examples as described herein. The controller 502 may be configured to track memory address of instructions associated with the memory 504. The controller 502 may be configured to decode instructions to determine the operation to be performed and the operands involved. For example, the controller 502 may be configured to interpret the instruction and determine control signals to be output to other components of the processor 500 to cause the processor 500 to support various operations in accordance with examples as described herein. Additionally, or alternatively, the controller 502 may be configured to manage flow of data within the processor 500. The controller 502 may be configured to control transfer of data between registers, arithmetic logic units (ALUs), and other functional units of the processor 500.

[0097] The memory 504 may include one or more caches (e.g., memory local to or included in the processor 500 or other memory, such RAM, ROM, DRAM, SDRAM, SRAM, MRAM, flash memory, etc. In some implementations, the memory 504 may reside within or on a processor chipset (e.g., local to the processor 500). In some other implementations, the memory 504 may reside external to the processor chipset (e.g., remote to the processor 500).

[0098] The memory 504 may store computer-readable, computer-executable code including instructions that, when executed by the processor 500, cause the processor 500 to perform various functions described herein. The code may be stored in a non- transitory computer-readable medium such as system memory or another type of memory. The controller 502 and / or the processor 500 may be configured to execute computer-readable instructions stored in the memory 504 to cause the processor 500 to perform various functions. For example, the processor 500 and / or the controller 502 may be coupled with or to the memory 504, the processor 500, the controller 502, and the memory 504 may be configured to perform various functions described herein. In some examples, the processor 500 may include multiple processors and the memory 504 may include multiple memories. One or more of the multiple processors may be coupledwith one or more of the multiple memories, which may, individually or collectively, be configured to perform various functions herein.

[0099] The one or more ALUs 506 may be configured to support various operations in accordance with examples as described herein. In some implementations, the one or more ALUs 506 may reside within or on a processor chipset (e.g., the processor 500). In some other implementations, the one or more ALUs 506 may reside external to the processor chipset (e.g., the processor 500). One or more ALUs 506 may perform one or more computations such as addition, subtraction, multiplication, and division on data. For example, one or more ALUs 506 may receive input operands and an operation code, which determines an operation to be executed. One or more ALUs 506 be configured with a variety of logical and arithmetic circuits, including adders, subtractors, shifters, and logic gates, to process and manipulate the data according to the operation. Additionally, or alternatively, the one or more ALUs 506 may support logical operations such as AND, OR, exclusive-OR (XOR), not-OR (NOR), and not-AND (NAND), enabling the one or more ALUs 506 to handle conditional operations, comparisons, and bitwise operations.

[0100] The processor 500 may support wireless communication in accordance with examples as disclosed herein. The processor 500 may be configured to or operable to support a means for: determining a set of encoder parameters for an encoder model of a two-sided model, transmitting encoded data to a second apparatus, wherein the encoded data is based on an input sample and the encoder model, and the input sample determines the input to the encoder model and a preferred output of the two-sided model, receiving a first set of information associated with an output of the two-sided model of a subset of the input sample, wherein the subset of the input sample is based on a first message from another apparatus or based on a relevance metric for each input sample of the subset of the input sample, and determining a model metric associated with performance of the two-sided model, wherein the model metric is based on the input sample and the first set of information.

[0101] Figure 6 illustrates an example of a NE 600 in accordance with aspects of the present disclosure. The NE 600 may include a processor 602, a memory 604, a controller 606, and a transceiver 608. The processor 602, the memory 604, the controller 606, or the transceiver 608, or various combinations thereof or variouscomponents thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.

[0102] The processor 602, the memory 604, the controller 606, or the transceiver 608, or various combinations or components thereof may be implemented in hardware (e.g., circuitry). The hardware may include a processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.

[0103] The processor 602 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof). In some implementations, the processor 602 may be configured to operate the memory 604. In some other implementations, the memory 604 may be integrated into the processor 602. The processor 602 may be configured to execute computer-readable instructions stored in the memory 604 to cause the NE 600 to perform various functions of the present disclosure. For example, the processor 602 coupled with the memory 604 may be configured to cause the NE 600 to: determine a set of decoder parameters for a decoder model of a two-sided model, receive an encoded data from a first apparatus, determine an output of the two-sided model based on the encoded data and the decoder model, and transmit a first set of information associated with the output of the two-sided model and a subset of the encoded data, wherein the subset of the encoded data is determined based on a first message received from another apparatus or based on a relevance metric determined for each encoded data.

[0104] The memory 604 may include volatile or non-volatile memory. The memory 604 may store computer-readable, computer-executable code including instructions when executed by the processor 602 cause the NE 600 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 604 or another type of memory. Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place toanother. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer.

[0105] In some implementations, the processor 602 and the memory 604 coupled with the processor 602 may be configured to cause the NE 600 to perform one or more of the functions described herein (e.g., executing, by the processor 602, instructions stored in the memory 604). For example, the processor 602 may support wireless communication at the NE 600 in accordance with examples as disclosed herein.

[0106] The controller 606 may manage input and output signals for the NE 600. The controller 606 may also manage peripherals not integrated into the NE 600. In some implementations, the controller 606 may utilize an operating system such as iOS®, ANDROID®, WINDOWS®, or other operating systems. In some implementations, the controller 606 may be implemented as part of the processor 602.

[0107] In some implementations, the NE 600 may include at least one transceiver 608. In some other implementations, the NE 600 may have more than one transceiver 608. The transceiver 608 may represent a wireless transceiver. The transceiver 608 may include one or more receiver chains 610, one or more transmitter chains 612, or a combination thereof.

[0108] A receiver chain 610 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 610 may include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 610 may include at least one amplifier (e.g., a low-noise amplifier (LNA)) configured to amplify the received signal. The receiver chain 610 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 610 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.

[0109] A transmitter chain 612 may be configured to generate and transmit signals (e.g., control information, data, packets). The transmitter chain 612 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM), frequency modulation (FM), or digital modulation schemes like phase-shift keying (PSK) orquadrature amplitude modulation (QAM). The transmitter chain 612 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 612 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.

[0110] Figure 7 illustrates a flowchart of a method 700 in accordance with aspects of the present disclosure. The operations of the method 700 may be implemented by a first apparatus (e.g., UE) as described herein. In some implementations, a UE 400 may execute a set of instructions to control the function elements of a processor to perform the described functions.

[0111] At 702, the method may include determining a set of encoder parameters for an encoder model of a two-sided model. The operations of 702 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 702 may be performed by a UE as described with reference to Figure 4.

[0112] At 704, the method may include transmitting encoded data to a second apparatus, wherein the encoded data is based on an input sample and the encoder model, and the input sample determines the input to the encoder model and a preferred output of the two-sided model. The operations of 704 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 704 may be performed by a UE as described with reference to Figure 4.

[0113] At 706, the method may include receiving a first set of information associated with an output of the two-sided model of a subset of the input sample, wherein the subset of the input sample is based on a first message from another apparatus or based on a relevance metric for each input sample of the subset of the input sample. The operations of 706 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 706 may be performed by a UE as described with reference to Figure 4.

[0114] At 708, the method may include determining a model metric associated with performance of the two-sided model, wherein the model metric is based on the input sample and the first set of information. The operations of 708 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 708 may be performed by a UE as described with reference to Figure 4.

[0115] Figure 8 illustrates a flowchart of another method 800 in accordance with aspects of the present disclosure. The operations of the method 800 may be implemented by a second apparatus (e.g., NE) as described herein. In some implementations, a NE 600 may execute a set of instructions to control the function elements of a processor to perform the described functions.

[0116] At 802, the method may include determining a set of decoder parameters for a decoder model of a two-sided model. The operations of 802 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 802 may be performed by a NE as described with reference to Figure 6.

[0117] At 804, the method may include receiving an encoded data from a first apparatus. The operations of 804 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 804 may be performed by a NE as described with reference to Figure 6.

[0118] At 806, the method may include determining an output of the two-sided model based on the encoded data and the decoder model. The operations of 806 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 806 may be performed by a NE as described with reference to Figure 6.

[0119] At 808, the method may include transmitting a first set of information associated with the output of the two-sided model and a subset of the encoded data, wherein the subset of the encoded data is determined based on a first message received from another apparatus or based on a relevance metric determined for each encoded data. The operations of 808 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 808 may be performed by a NE as described with reference to Figure 6.

[0120] Figure 9 illustrates a flowchart of a method 900 in accordance with aspects of the present disclosure. The operations of the method 900 may be implemented by a first apparatus (e.g., UE) as described herein. In some implementations, a UE 400 may execute a set of instructions to control the function elements of a processor to perform the described functions.

[0121] At 902, the method may include determining a set of encoder parameters for an encoder model of a two-sided model. The operations of 902 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 902 may be performed by a UE as described with reference to Figure 4.

[0122] At 904, the method may include transmitting encoded data to a second apparatus, wherein the encoded data is based on an input sample and the encoder model, and the input sample determines the input to the encoder model and a preferred output of the two-sided model. The operations of 904 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 904 may be performed by a UE as described with reference to Figure 4.

[0123] At 906, the method may include determining a subset of the input sample based on a relevance metric or a first message from another apparatus. The operations of 906 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 906 may be performed by a UE as described with reference to Figure 4.

[0124] At 908, the method may include transmitting a first set of information associated with the preferred output of the two-sided model of the subset of the input sample. The operations of 908 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 908 may be performed by a UE as described with reference to Figure 4.

[0125] Figure 10 illustrates a flowchart of another method 1000 in accordance with aspects of the present disclosure. The operations of the method 1000 may be implemented by a second apparatus (e.g., NE) as described herein. In some implementations, a NE 600 may execute a set of instructions to control the function elements of a processor to perform the described functions.

[0126] At 1002, the method may include determining a set of decoder parameters for a decoder model of a two-sided model. The operations of 1002 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1002 may be performed by a NE as described with reference to Figure 6.

[0127] At 1004, the method may include receiving an encoded data from a first apparatus. The operations of 1004 may be performed in accordance with examples asdescribed herein. In some implementations, aspects of the operations of 1004 may be performed by a NE as described with reference to Figure 6.

[0128] At 1006, the method may include determining an output of the two-sided model based on the encoded data and the decoder model. The operations of 1006 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1006 may be performed by a NE as described with reference to Figure 6.

[0129] At 1008, the method may include receiving a first set of information associated with a preferred output of the two-sided model of a subset of the encoded data, wherein the subset of the encoded data is determined based on a first message received from another apparatus or based on a relevance metric determined for each encoded data. The operations of 1008 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1008 may be performed by a NE as described with reference to Figure 6.

[0130] At 1010, the method may include determining a model metric related to performance of the two-sided model, wherein the model metric is based on the output of the two-sided model and the first set of information. The operations of 1010 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1010 may be performed by a NE as described with reference to Figure 6.

[0131] It should be noted that the methods described herein describe possible implementations, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible.

[0132] The description herein is provided to enable a person having ordinary skill in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to a person having ordinary skill in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described herein but is to be accorded the broadest scope consistent with the principles and novel features disclosed herein.

Claims

CLAIMS What is claimed is:

1. A first apparatus, comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the first apparatus to: determine a set of encoder parameters for an encoder model of a two-sided model; transmit encoded data to a second apparatus, wherein the encoded data is based on an input sample and the encoder model, and the input sample determines the input to the encoder model and a preferred output of the two-sided model; receive a first set of information associated with an output of the two-sided model of a subset of the input sample, wherein the subset of the input sample is based on a first message from another apparatus or based on a relevance metric for each input sample of the subset of the input sample; and determine a model metric associated with performance of the two-sided model, wherein the model metric is based on the input sample and the first set of information.

2. The first apparatus of claim 1, wherein the at least one processor is configured to cause the first apparatus to transmit a second message based on the subset of the input sample, and the second message requests a corresponding output of the two-sided model associated with the subset of the input sample.

3. The first apparatus of claim 1, wherein the preferred output of the two-sided model is the same as the input of the encoder model of the two-sided model.

4. The first apparatus of claim 1, wherein the first set of information is received from the second apparatus or another apparatus.

5. The first apparatus of claim 1, wherein the input sample is based on a channel data representation.

6. The first apparatus of claim 5, wherein the channel data representation is determined based on reception of a reference signal from the second apparatus.

7. The first apparatus of claim 5, wherein the channel data representation is based on different transmit (TX)-receive (RX) pairs over different frequency bands or different time slots or TX-RX pair transformations in other domains.

8. A second apparatus, comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the second apparatus to: determine a set of decoder parameters for a decoder model of a two-sided model; receive an encoded data from a first apparatus; determine an output of the two-sided model based on the encoded data and the decoder model; and transmit a first set of information associated with the output of the two-sided model and a subset of the encoded data, wherein the subset of the encoded data is determined based on a first message received from another apparatus or based on a relevance metric determined for each encoded data.

9. The second apparatus of claim 8, wherein the at least one processor is configured to cause the second apparatus to transmit, to the first apparatus or another apparatus, a second message based on the subset of the encoded data.

10. The second apparatus of claim 8, wherein the set of encoded parameters is received from another apparatus.

11. A first apparatus, comprising:at least one memory; and at least one processor coupled with the at least one memory and configured to cause the first apparatus to: determine a set of encoder parameters for an encoder model of a two-sided model; transmit encoded data to a second apparatus, wherein the encoded data is based on an input sample and the encoder model, and the input sample determines the input to the encoder model and a preferred output of the two-sided model; determine a subset of the input sample based on a relevance metric or a first message from another apparatus; and transmit a first set of information associated with the preferred output of the two-sided model of the subset of the input sample.

12. The first apparatus of claim 11, wherein the at least one processor is configured to cause the first apparatus to transmit a second message based on the subset of the input sample.

13. The first apparatus of claim 11, wherein the set of encoder parameters is received from another apparatus.

14. The first apparatus of claim 11, wherein the preferred output of the two-sided model is the same as the input of the encoder model of the two-sided model.

15. The first apparatus of claim 11, wherein the first set of information is received from the second apparatus or another apparatus.

16. The first apparatus of claim 11, wherein the input sample is based on a channel data representation.

17. The first apparatus of claim 16, wherein the channel data representation is determined based on reception of a reference signal from the second apparatus.

18. The first apparatus of claim 16, wherein the channel data representation is based on different transmit (TX)-receive (RX) pairs over different frequency bands or different time slots or TX-RX pair transformations in other domains.

19. A second apparatus, comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the second apparatus to: determine a set of decoder parameters for a decoder model of a two-sided model; receive an encoded data from a first apparatus; determine an output of the two-sided model based on the encoded data and the decoder model; receive a first set of information associated with a preferred output of the two-sided model of a subset of the encoded data, wherein the subset of the encoded data is determined based on a first message received from another apparatus or based on a relevance metric determined for each encoded data; and determine a model metric related to performance of the two-sided model, wherein the model metric is based on the output of the two-sided model and the first set of information.

20. The second apparatus of claim 19, wherein the at least one processor is configured to cause the second apparatus to transmit, to the first apparatus or another apparatus, a second message based on the subset of the encoded data, and the second message requests a corresponding output of the two-sided model associated with the subset of the encoded data.

Images