Automated Collaborator Selection for Federated Learning with Multi-armed Bandit Agents.

Hannes Larsson Hassam Riaz Selim Ickin

Published in: FlexNets@SIGCOMM (2021)

Keyphrases

multi agent
learning algorithm
multi agent systems
learning process
learning problems
active learning
supervised learning
learning tasks
reinforcement learning
hidden variables
multi armed bandits