Fast Meta Failure Recovery for Federated Meta-Learning

Chao Wang

Abstract:

In recent years, the ffeld of distributed deep learning
within the Internet of Things (IoT) or the edge has experienced
exponential growth. Federated meta-learning has emerged as a
signiffcant advancement, enabling collaborative learning among
source nodes to establish a global model initialization. This
approach allows for optimal performance while necessitating
minimal data samples for updating model parameters at the
target node. Federated meta-learning has gained increased attention
due to its capacity to provide real-time edge intelligence.
However, a critical aspect that remains inadequately explored
is the recovery of interim meta knowledge’s failure, which
constitutes a pivotal key for adapting to new tasks. In this
paper, we introduce FMRec, a novel platform designed to offer
a fast and ffexible recovery mechanism for failed interim meta
knowledge in various federated meta-learning scenarios. FMRec
serves as a complementary system compatible with different
types of federated models and is adaptable to diverse tasks. We
present a demonstration of its design and assess its efffciency and
reliability through real-world applications.