DICE defines and approximates multi-hop data influence in decentralized learning, showing that influence is shaped by data, topology, and loss curvature.
andH(θt+1 k ; zt+1 k ) denotes the Hessian matrix of L with respect to θt+1 k evaluated at zt+1 k
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
-
DICE: Data Influence Cascade in Decentralized Learning
DICE defines and approximates multi-hop data influence in decentralized learning, showing that influence is shaped by data, topology, and loss curvature.