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 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: 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 is provided. The method includes generating a first data by using a first decoder model with a first set of target features, wherein the first decoder model is based on the first source domain. The method includes updating a final set of target features and final data based on the generated first data. The method includes generating a second data by using a second decoder model with a second set of target features, wherein the second data that is generated is conditioned on the first set of target features and wherein the second decoder model is based on the second source domain. The method includes updating the final set of target features and final data based on the generated second data. The method includes training a target-domain model using the final data and the final set of target features.

Abstract: Embodiment herein disclose a method performed a network node for energy harvesting. The transmitter, the receiver unit operate in the network node. The receiver unit is positioned at a distance ‘d’ from the transmitter to produce a first amount of electrical energy. Further, the performance parameters are collected by a control unit from at least one wireless device to determine a preferred distance required between the receiver unit and the transmitter. Thereafter, the position of the receiver unit is adjusted by the control unit, at the preferred distance to the transmitter to harvest a second amount of electrical energy, where second amount is greater than the first amount. Further, at least one of the first amount or second amount of electrical energy harvested by the receiver unit is stored in a power distribution unit.

Abstract: There is provided a method performed by a master node for managing training of a machine learning model. One or more worker nodes of a plurality of worker nodes are selected to train a machine learning model in a round of training. The one or more worker nodes are selected to optimize a performance of an updated machine learning model for a validation dataset after the round of training. The updated machine learning model has one or more parameters of the machine learning model trained by the one or more worker nodes in a previous round of training.

Abstract: A computer implemented method of managing power control in a communication system includes generating a graph representation of interdependencies of components of the communication system, wherein the graph representation includes graph nodes corresponding to the components of the communication system and edges between pairs of graph nodes representing dependency relationships between the pairs of nodes. The method generates edge weights for the edges of the graph representation that correspond to the relative importance of the dependency relationship represented by the edge weight, and generates a policy for managing power control by determining an order for switching the components of the communication system on or off based on the edge weights.

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: Methods include training, using a generative adversarial network, a generator model using data noise that includes data corresponding to real problems of a telecommunication site, generating a generated problem that has not occurred at the telecommunication site and that has a non-zero probability of occurring at the site in the future, providing the generated problem to a virtual agent that is configured to generate a solution action to resolve the generated problem, evaluating the solution action relative to the generated problem to determine a performance value corresponding to the solution action, and responsive to the performance value being higher than other performance values corresponding to other solution actions for the generated problem, generating a generic problem model that corresponds to the generated problem and that is associated with the solution action.

Abstract: Managing network event data in a telecommunication network. The method includes obtaining a plurality of datasets having network event data associated with products provided by a different vendor, the network event data comprising a plurality of data instances representing a plurality of network event features. The method further comprises obtaining metadata describing the network event data in the datasets and generating feature description vectors from the obtained metadata, calculating a metric of the relation between network event features represented in the datasets and constructing a graph of the network event features represented in the datasets, with edges weighted according to the calculated metric, partitioning the graph into clusters by minimising an edge cut between network event features, labelling network event features in the cluster with a normalised network event feature index and inputting the labelled network event data to a model for making at least one of recommendations or predictions.

Abstract: Embodiments disclosed herein relate to methods and apparatus for generating video frames when there is a change in the rate of received video data. In one embodiment there is provided a method of processing video data which comprises generating a video frame using received video data, encoding said video frame into a latent vector using an encoder part of a generative model, modifying the latent vector and decoding the modified latent vector using a decoder part of the generative model to generate a new video frame in response to determining a reduction in generating the video frames using the received video data.

Abstract: There is provided a method comprising: acquiring (110) sensor data related to an object; using the first learning module, identifying (120) the object based on the acquired sensor data using a first learning module and determining (130) a user associated with the identified object; determining (140) a timestamped location of the object based on at least one of the acquired sensor data and one or more locations of the one or more sensors; performing (150) a first analysis to determine whether the current status of the object contains an anomaly based on one or more predefined rules stored in a knowledge base; performing (160) a second analysis to determine whether the current status of the object contains an anomaly, using a second learning module; and validating (170) whether the current status of the object contains an anomaly based on results of the first analysis and results of the second analysis.

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.

Abstract: A method performed by a node in a telecommunications network for managing faults includes obtaining predictions of faults in the telecommunications network and time intervals in which the faults are predicted to occur. The method then includes determining possible actions that could be performed to address the predicted faults and associated resource usages to perform the possible actions, and selecting actions to perform, from the possible actions, in order to address the predicted faults, based on the predicted time intervals and the determined resource usages.

Abstract: An initial bitrate is selected for a video delivery session by a user equipment (5, 200) performing, during a time window from initiation of a video player application in the user equipment (5, 200) up to selection of a video content, network measurements of a current condition of a network used to deliver the video content to the user equipment (5, 200). A respective initial buffer duration is provided for each bitrate available for the video content and where these respective initial buffer durations are predicted based on at least one network metric derived from the network measurements. An initial bitrate for delivering the video content over the network to the user equipment is selected based on the respective initial buffer durations.

Abstract: Methods, systems, apparatuses and computer programs are presented for developing machine-learning models. A method for decentralized machine learning in a target worker node comprises: receiving a plurality of adapted neural network models from a plurality of worker nodes, wherein each of the adapted neural network models is generated by training a worker node neural network using local data of the worker node from among the plurality of worker nodes; selecting, from the plurality of adapted neural network models, a set of adapted neural network models that satisfy performance criteria when local data of the target worker node is input; and averaging the set of adapted neural network models to generate an average model.

Abstract: Communications from a content server to an end device via a proxy device are controlled. The content server and the proxy device are connected by a first link using a streaming control protocol. The proxy device also has a connection to the end device over a second link. The method includes obtaining information about a context of the end device. The method further includes determining where a decision should be made about controlling transmissions from the content server over the first link, based on the information about the context of the end device. The method further includes controlling transmissions from the content server over the first link, based on information relating to a Quality of Experience at the end device.

Abstract: A method (300) for using federated learning to develop a machine-learning model is disclosed. The method, performed by a management function, comprises developing a seed version of the machine-learning model using a machine-learning algorithm (310) and communicating the seed version of the machine-learning model to a plurality of distributed nodes, each of the plurality of distributed nodes being associated with a local data set (320).

Abstract: A method of generating a synthetic training dataset for training a machine learning model using an original training dataset including a plurality of features includes selecting a feature ci of the original training dataset as a target vector yi, selecting remaining features of the original training dataset as a set of training input vectors X\i, where X\i includes all features of the training dataset other than a feature corresponding to the selected feature ci, and training a prediction model f(yi|X\i). The method generates an estimate y?i of the target vector yi by applying the prediction model to the set of training vectors X\i, and inserts a synthetic feature c?i corresponding to the estimate y?i of the target vector yi into a synthetic training dataset.

Abstract: A method performed by a central server node in a distributed machine learning environment is provided. The method includes: managing distributed machine learning for a plurality of local client nodes, such that a first set of the plurality of local client nodes are assigned to assist training of a first central model and a second set of the plurality of local client nodes are assigned to assist training of a second central model; obtaining information regarding network conditions for the plurality of local client nodes; clustering the plurality of local client nodes into one or more clusters based at least in part on the information regarding network conditions; re-assigning a local client node in the first set to the second set based on the clustering; and sending to the local client node a message including model weights for the second central model.