FRAIN combines a two-proposal FastSync approximation with SLERP-based merging to make decentralized asynchronous federated learning more robust to non-IID data, stale updates, and malicious nodes.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FRAIN to Train: A Fast-and-Reliable Solution for Decentralized Federated Learning
FRAIN combines a two-proposal FastSync approximation with SLERP-based merging to make decentralized asynchronous federated learning more robust to non-IID data, stale updates, and malicious nodes.