Distribute the computation for better efficiency.
(E.g. computing power,
workload, storage management)
Collaborate with the intent to keep the data of each agent heterogenous, local and private.
Federated learning can be centralized, decentralized and semi-centralized.
Efficient allocation and execution of the tasks in the appropriate
heterogeneous and dynamic distributed computing devices that are
connected at the edge level.
Predict better for futur data. In online settings, data becomes available in a sequential order.