An algorithm that filters neighbor updates by cumulative trust scores, aiming for sublinear regret in online decentralized federated multi-task learning with a Byzantine majority.
Resilience to malicious activity in distributed optimization for cyberphysical systems,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Online Decentralized Federated Multi-task Learning With Trustworthiness in Cyber-Physical Systems
An algorithm that filters neighbor updates by cumulative trust scores, aiming for sublinear regret in online decentralized federated multi-task learning with a Byzantine majority.