Formulates a game where competitors in collaborative learning are incentivized to manipulate updates, then proposes mechanisms that restore honest participation for mean estimation, convex SGD, and non-convex federated learning.
Optimum statistical estimation with strategic data sources
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Incentivizing Honesty among Competitors in Collaborative Learning and Optimization
Formulates a game where competitors in collaborative learning are incentivized to manipulate updates, then proposes mechanisms that restore honest participation for mean estimation, convex SGD, and non-convex federated learning.