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: A computer implemented method performed by a node in a communications network comprises obtaining Key Performance Indicator, KPI, targets for a plurality of KPIs, in the communications network, and determining relationships between the KPIs using a model trained using a graph-based machine learning process. Each relationship describes a manner in which changing a network configuration to alter a first one of the plurality of KPIs affects a second one of the plurality of KPIs. The method then comprises determining one or more conflicts between the KPI targets, using the relationships.

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 computer implemented method performed by a node in a communications network comprises obtaining Key Performance Indicator, KPI, targets for a plurality of KPIs, in the communications network, and determining relationships between the KPIs using a model trained using a graph-based machine learning process. Each relationship describes a manner in which changing a network configuration to alter a first one of the plurality of KPIs affects a second one of the plurality of KPIs. The method then comprises determining one or more conflicts between the KPI targets, using the relationships.

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: 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 reinforcement learning (RL) process is used to allocate UL/DL resources and is also used to offload traffic from a first access point (e.g., macro access point) to a second access point (e.g., a micro access point) when the load on the first access point is too high. The RL process is able to handle the dynamic nature of UL/ DL imbalances and is therefore able to maximize usage of resources without compromising quality of service.