Sampling user equipment for federated learning model collection

Abstract

First user equipments are detected out of a plurality of user equipments of a cellular communication system (S). The user equipments respectively correspond to a distributed node of a federated machine-learning concept and respectively generate a partial machine-learning model, wherein partial machine-learning models generated by the plurality of user equipments are to be used to update a global machine-learning model at the network side of the cellular communication system. The first user equipments are user equipments comprising ready partial machine-learning models. Out of the first user equipments, second user equipments are selected at least based on a time information associated with the first user equipments (S), the ready partial machine-learning models respectively generated by the second user equipments are acquired (S), the global machine-learning model is updated using the ready partial machine-learning models acquired (S), and convergence of the global machine-learning model updated by the ready partial machine-learning models acquired is determined (S). In case convergence of the Sglobal machine-learning model is not determined, a process comprising the detecting (S), selecting (S), acquiring (S), updating (S) and determining (S) is repeated.