A gossip learning framework with history-aware peer sampling and an adaptive aggregation threshold keeps accuracy within about 5% of the no-attack baseline when 30% of nodes are Byzantine.
Exponential graph is provably efficient for decentralized deep training,
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
-
GRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework
A gossip learning framework with history-aware peer sampling and an adaptive aggregation threshold keeps accuracy within about 5% of the no-attack baseline when 30% of nodes are Byzantine.