Proto-EVFL selects useful unaligned data in vertical federated learning with a dual optimal transport cost and class priors, then aggregates party features with learned gates, improving accuracy on rare and unseen classes.
Bilevel optimization: Convergence analysis and enhanced design,
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
-
Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data
Proto-EVFL selects useful unaligned data in vertical federated learning with a dual optimal transport cost and class priors, then aggregates party features with learned gates, improving accuracy on rare and unseen classes.