Privacy-aware bucketing plus parameter-level shuffling disrupts non-IID gradient structure in HDP-FL, cutting recoverability >60% and surrogate accuracy from 0.78 to 0.33 while preserving ε-aware aggregation utility.
arXiv preprint arXiv:2101.05428 , year=
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
years
2026 8representative citing papers
ELCP integrates auxiliary data with a density-ratio-weighted kernel to enhance localized conformal prediction sets, maintaining marginal coverage and improving asymptotic local coverage.
DIST-FL distributes TEE-guarded servers into an append-only ledger to ensure linearizable FL aggregation and counter rollback plus I/O attacks while matching single-TEE speed.
Derives tractable optimal fair multi-class classifier and supplies in-processing and post-processing algorithms that converge to the accuracy-fairness Pareto frontier.
StCP leverages transfer learning to stabilize the size of conformal prediction sets without additional target labels.
DFL-AA removes link-quality distortion in expectation from gossip aggregation in asynchronous decentralized federated learning by combining online IPW for selection bias correction with AoI weighting for staleness mitigation.
FedHD is a federated learning framework for whole slide images that distills one-to-one synthetic features aligned via Gaussian mixtures and progressively integrates cross-site features through curriculum learning to handle institutional heterogeneity.
FL with homomorphic encryption matches centralized ML performance for CVD risk prediction but adds cryptographic overhead, while DP-FL has lower cost yet greater accuracy loss especially for logistic regression.
citing papers explorer
-
IntraShuffler: A Privacy Preserving Framework for Heterogeneous DP Federated Learning
Privacy-aware bucketing plus parameter-level shuffling disrupts non-IID gradient structure in HDP-FL, cutting recoverability >60% and surrogate accuracy from 0.78 to 0.33 while preserving ε-aware aggregation utility.
-
Enhanced localized conformal prediction with imperfect auxiliary information
ELCP integrates auxiliary data with a density-ratio-weighted kernel to enhance localized conformal prediction sets, maintaining marginal coverage and improving asymptotic local coverage.
-
DIST-FL: Enhancing Security for TEE-based Aggregation in Federated Learning
DIST-FL distributes TEE-guarded servers into an append-only ledger to ensure linearizable FL aggregation and counter rollback plus I/O attacks while matching single-TEE speed.
-
Demystifying the Optimal Fair Classifier in Multi-Class Classification
Derives tractable optimal fair multi-class classifier and supplies in-processing and post-processing algorithms that converge to the accuracy-fairness Pareto frontier.
-
Stable Localized Conformal Prediction via Transduction
StCP leverages transfer learning to stabilize the size of conformal prediction sets without additional target labels.
-
Asynchronous Decentralized Federated Learning over Lossy Wireless Links via Reception- and Age-Aware Aggregation
DFL-AA removes link-quality distortion in expectation from gossip aggregation in asynchronous decentralized federated learning by combining online IPW for selection bias correction with AoI weighting for staleness mitigation.
-
Federated Distillation for Whole Slide Image via Gaussian-Mixture Feature Alignment and Curriculum Integration
FedHD is a federated learning framework for whole slide images that distills one-to-one synthetic features aligned via Gaussian mixtures and progressively integrates cross-site features through curriculum learning to handle institutional heterogeneity.
-
Privacy-Preserving Federated Learning via Differential Privacy and Homomorphic Encryption for Cardiovascular Disease Risk Modeling
FL with homomorphic encryption matches centralized ML performance for CVD risk prediction but adds cryptographic overhead, while DP-FL has lower cost yet greater accuracy loss especially for logistic regression.