Abstract: Methods and systems for power supply unit (PSU) control. A method includes measuring one or more properties of the PSU to obtain property measurements, and initiating transmission of the property measurements to a machine learning (ML) agent hosting a trained ML model. The method further includes receiving the property measurements at the ML agent, and processing the received property measurements using the trained ML model to generate suggested actions to be taken by the PSU. The method further includes predicting the effect of each of the suggested actions on the measured PSU properties, and selecting a subset of the suggested actions predicted to have a significant impact on the measured PSU properties. The method further includes initiating transmission of the selected subset of suggested actions to the PSU, and performing, at the PSU, the selected subset of suggested actions.

Abstract: A method of operating a master node in a vertical federated learning, vFL, system including a plurality of workers for training a split neural network includes receiving layer outputs for a sample period from one or more of the workers for a cut-layer at which the neural network is split between the workers and the master node, and determining whether layer outputs for the cut-layer were not received from one of the workers. In response to determining that layer outputs for the cut-layer were not received from one of the workers, the method includes generating imputed values of the layer outputs that were not received, calculating gradients for neurons in the cut-layer based on the received layer outputs and the imputed layer outputs, splitting the gradients into groups associated with respective ones of the workers, and transmitting the groups of gradients to respective ones of the workers.

Abstract: A method performed by a control node (800) for determining whether two wireless devices meet a location criterion for closeness, the method comprising: obtaining (701), from the two wireless devices, measurements of a reference signal transmitted in a beam by a radio network node to a plurality of measurement points that are spatially distributed around the two wireless devices; and determining (702) whether the two wireless devices meet the location criterion based on the obtained measurements.

Abstract: A method is provided for determining bias of machine learning models. The method includes: forming a training dataset including input data samples provided to a remote machine learning model developed using a machine learning process, and corresponding output data samples obtained from the remote machine learning model; training a local machine learning model which approximates the remote machine learning model using a machine learning process and the training dataset; and interrogating the trained local machine learning model to determine whether the remote machine learning model is biased with respect to one or more biasing data parameters.

Abstract: A computer-implemented method performed by a network node is provided. The method includes receiving a request for retrieving or executing a machine learning (ML) model or a combination of ML models. The request includes a first description of a specified output feature and specified input data type and distribution of input values for a ML model or combination of ML models. The method further includes obtaining an identification of a ML model, or a combination of ML models, having a second description that at least partially satisfies a match to the first description; identifying a candidate ML model, or combination of ML models, that produces the specified output feature of the first description based on a comparison of the first and second descriptions. The method further includes selecting a third description of the identified candidate ML model, or combination of ML models, based on a convergence.

Abstract: According to a second aspect, it is provided a method for enabling collaborative machine learning. The method is performed by an agent device. The method includes the steps of: obtaining local input data; generating read interface parameters based on the local input data using a controller neural net; generating write interface parameters; transmitting a central reading request to the central device; receiving a central reading from the central device; updating the controller neural net of the agent device based on the central reading; and providing a predictor output of local input data based on the controller neural net and a second model of the agent device, the second model having as an input an output of the controller neural net, wherein the predictor output is obtained from the second model.

Abstract: A method of operating a protection node for protecting a pattern classification node from malicious requests may be provided. The protection node may receive, from a user node, a request containing an original pattern to be classified by a machine learning algorithm performed by the pattern classification node. The protection node may add noise to the original pattern to generate a noisy pattern. The protection node may obtain a first classification of the noisy pattern based on processing of the noisy pattern by a first clone of the machine learning algorithm at the protection node; obtain a second classification of the original pattern based forwarding the request for processing of the original pattern by the machine learning algorithm performed at the pattern classification node; and compare the first and second classifications to determine whether the first and second classifications satisfy a defined similarity rule. The protection node may use the comparison to manage the request from the user node.

Abstract: The present disclosure relates to techniques for providing and facilitating time-controlled data for preserving privacy of data sources. Embodiments are provided herein for methods, processes, devices, network nodes, computer program products, and computer-readable media. In some embodiments, a network node receives first data for a first data transaction that is assigned a unique identifier. In response, the network node enables transmission of second data and the unique identifier to one or more entity. In accordance with a determination that an indication of the time limit indicates a non-zero time limit for retention of the first data for the first data transaction, the node enables storage of one or more of the first data and the second data according to the time limit. In accordance with a determination that the indication does not indicate a non-zero time limit, the node causes deletion of the first data and the second data.

Abstract: A computer implemented method performed by a node in a communications network for scheduling transmissions of a plurality of Internet of Things (IoT) devices to network resources in the communications network includes obtaining transmission patterns for the IoT devices. The method then includes clustering the IoT devices into clusters based on the obtained transmission patterns. The method then includes scheduling transmissions of IoT devices in different clusters to different network resources, thereby increasing synchronisation of the transmissions scheduled on each network resource and allowing for increased periods of inactivity of the network resources between transmissions.

Abstract: An operator system of a wireless communication network operator sends, to a regulator system of a regulator, a record that includes information about administration of a subscription identifier associated with the wireless communication network operator. Responsive to sending the record to the regulator system, the operator system receives a response that indicates whether the regulator system approves of or rejects the record being added to a permissioned distributed database that is distributed at least in part between the regulator system and the operator system. The operator system adds or does not add the record to the permissioned distributed database depending on the response.

Abstract: Methods (500) and devices (800) for determining a priority level for a first application or a first application type. The method comprises receiving (s502) a first usage data reporting message, the first usage data reporting message comprising a first masked usage value generated by a first UE (102) using i) a first usage value associated with a first application or a first application type and ii) a mask value. The method further comprises receiving (s504) a second usage data reporting message, the second usage data reporting message comprising a second masked usage value generated by a second UE (104) using i) a second usage value associated with the first application or the first application type and ii) the mask value. The method further comprises combining (s506) the first masked usage value and the second masked usage value, thereby generating a combined usage value; and using (s508) the combined usage value to determine a priority level for the first application or the first application type.

Abstract: There is provided a method performed by an entity for managing connectivity of a device to a network. The method comprises selecting, from a plurality of connectivity service providers in the network, a connectivity service provider (CSP) to connect the device to the network. The selection is based on information about the device.

Abstract: A method performed by a computing device for a radio network for configuration of a network device on which network or data energy can be collected while preserving specified conditions in the radio network is provided. The method includes receiving inputs to a conditional generative model. The inputs include the specified conditions in the radio network including a value for a predicted key performance indicator, KPI, constraint parameter for a time period, a target value for a optimization parameter, and a latent variable. The method further includes outputting from the conditional generative model a configuration data for a future time period for the network node or the cell of the radio network. The configuration data is bounded by the specified conditions including the predicted KPI constraint parameter, the target value for the optimization parameter, and the latent variable.

Abstract: A method by a WiFi AP for setting-up a WiFi connection with a wireless device, includes sending WiFi service credentials to a Light Fidelity (Li-Fi) AP for transmission through Li-Fi signaling that is broadcast for reception by wireless devices. The method receives and authenticates an authentication request that is received via a RF transceiver of the WiFi AP from the wireless device, which is responding to the WiFi service credentials that were broadcast through the Li-Fi signaling. The method then establishes a WiFi RF connection with the wireless device responsive to the authentication.

Abstract: Embodiments described herein relate to methods and apparatuses for training a neural network. A method comprises receiving an input data set at a layer of the neural network; performing a forward pass and a backward pass on the input data set to determine regular output data; calculating a first loss associated with the regular output data; performing a quantized forward pass and a quantized backward pass on the input data set to determine quantized output data; calculating a second loss associated with the quantized output data; comparing the first loss to the second loss; and based on the comparison determining whether to reduce the input data set to provide a reduced data set.

Abstract: Methods and central nodes for developing machine-learning models, the method including receiving, at a central node, at least one episode including a plurality of changes of an environment. The method further includes analysing the episode to extract observations and grouping the observations from among the plurality of observations into a plurality of groups of similar observations. A first machine learning agent is then trained using a first group of similar observations from among the plurality of groups of similar observations, and a second machine learning agent is trained using a second group of similar observations from among the plurality of groups of similar observations, wherein the second group of similar observations is different to the first group of similar observations. The central node obtains a central machine-learning model based on an output from at least one of the trained first machine learning agent and the trained second machine learning agent.

Abstract: There is provided a method for handling training of a machine learning model. The method is performed by a coordinating entity that is operable to coordinate the training of the machine learning model at one or more network nodes. In response to receiving a request to train the machine learning model, a first network node is selected (402), from a plurality of network nodes, to train the machine learning model based on information indicative of a performance of each of the plurality of network nodes and/or information indicative of a quality of a network connection to each of the plurality of network nodes. Transmission of the machine learning model is initiated (404) towards the first network node for the first network node to train the machine learning model.

Abstract: A testing system and method for testing a Printed Circuit Boards (PCBs) is provided. The method is being executed at a testing system which comprises a RF test analyzer; a RF energy source; and one or more RF probes. The method includes performing a first level scanning of a first set of components in the PCB. The method further includes performing a second level scanning of another set of components in the PCB, which differs from the first set of components in the PCB; the second level scanning is performed only if anomalies are identified which is based on analyzing the results of the performed first level scanning. The method further includes determining detailed root causes of the identified anomalies which is based on analyzing results of the performed second level scanning.

Abstract: Methods and sewer nodes generate machine learning models using models trained locally while avoiding misinformation by selectively aggregating models trained locally using data stored in client devices, which are connected to the server node via a communication network. The client devices receive an initial model and return updated model parameters of a respective model locally trained. Logical explanations are obtained, for each of the client devices, based on the updated model parameters and at least one set of input and corresponding output values. A distance based on the logical explanations, for each client device in a secondary cluster, measures a deviation of the respective model relative to model(s) of client devices in a primary cluster. The output model is generated by selectively aggregating at least the models received from the client devices in the primary cluster, while assessing each client device in the secondary cluster based on the distance thereof.

Abstract: A method in a first node of a communications network for training a machine learning model comprises receiving a first message comprising instructions for training the machine learning model using a distributed learning process. The method then comprises responsive to receiving the first message, acting as an aggregator in the distributed learning process for a subset of other nodes selected by the first node from a plurality of nodes that have an established radio channel allocation with the first node, by causing the subset of other nodes to perform training on local copies of the machine learning model and aggregating the results of the training by the subset of other nodes.