… federated learning algorithms, which have general applicability to a wide range of machine
learning … the complete control algorithm for adaptive federated learning, which recomputes τ …

… an adaptive asynchronous federated learning (AAFL) mechanism for edge computing, and
… We then propose experience-driven algorithms based on deep reinforcement learning (DRL…

… , FedAda (Federated Adaptive Training), that incorporates systems capabilities and data …
as in Federated Averaging (FedAvg), our algorithm adopts an adaptive workload assignment …

… the approach to adapting the proposed method to the real-world edge computing environment
in Section … to the proposed algorithm for adapting to the real edge computing environment. …

… federated learning has been widely used in collaborative training of machine learning …
non-IID data issue, we present an adaptive clustered federated learning approach, \(\mathtt {…

… allocation for VNF and adaptive model transmission in SDN-based IoT, a system model is
vital for adopting SDN/NFV-based architecture and integrating with edge computing systems. …

… adaptive gradient compression, we can apply it in general federated learning designed for
industrial edge computing… the federated learning into five steps: edge terminal computing, …

… Due to edge heterogeneity, we adopt the adaptive learning rate for model training, which
will be discussed in Section II-D. Then worker vi uploads its updated local model wi …

… adaptive optimisation when updating the global model on the server. Reddi et al. [16] also
generalised other adaptive … method presented here uses adaptive optimisation on clients, …

… Distributed DNN models are well adapted to EC. To collectively train the DL model, the … We
analyzed the implementation of federated learning in an edge computing environment based …