Derives heterogeneity bounds separating objective-shift and feasible-set-shift effects in decision-focused federated learning and shows federation benefits when statistical gains exceed client-specific penalties.
A survey on heterogeneous federated learning.arXiv preprint arXiv:2210.04505
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Metropolis-Hastings with Levy jumps prevents entrapment in weighted random walks, yielding a convergence rate that accounts for data heterogeneity, network spectral gap, and jump probability.
A federated RuleFit method using differentially private histograms for consistent cutoffs, local GBDT rule generation, and federated dual averaging for l1-regularized coefficients matches centralized RuleFit performance in simulations and delivers interpretable results on real medical data.
A framework automates federated learning aggregation strategy selection via LLM inference in single-trial mode and genetic search in multi-trial mode, improving robustness under non-IID data.
citing papers explorer
-
Decision-Focused Federated Learning Under Heterogeneous Objectives and Constraints
Derives heterogeneity bounds separating objective-shift and feasible-set-shift effects in decision-focused federated learning and shows federation benefits when statistical gains exceed client-specific penalties.
-
Decentralized Learning via Random Walk with Jumps
Metropolis-Hastings with Levy jumps prevents entrapment in weighted random walks, yielding a convergence rate that accounts for data heterogeneity, network spectral gap, and jump probability.
-
Federated Rule Ensemble Method in Medical Data
A federated RuleFit method using differentially private histograms for consistent cutoffs, local GBDT rule generation, and federated dual averaging for l1-regularized coefficients matches centralized RuleFit performance in simulations and delivers interpretable results on real medical data.
-
Automating aggregation strategy selection in federated learning
A framework automates federated learning aggregation strategy selection via LLM inference in single-trial mode and genetic search in multi-trial mode, improving robustness under non-IID data.