BESplit mitigates non-IID bias in split federated learning via evidential aggregation, bias-compensated client pairing, and dual-teacher distillation, outperforming prior methods on five benchmarks.
arXiv preprint arXiv:2111.04263 , year=
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
years
2026 8verdicts
UNVERDICTED 8representative citing papers
Federated PEFT on LLMs across healthcare and finance datasets performs close to centralized training and beats isolated local training under non-IID conditions.
Fed3D is a federated 3D object detection system using local-global class-aware loss for heterogeneity and prompt modules for low-bandwidth communication, claiming better performance than prior methods on limited local data.
FedQuad uses quadruplet constraints and stochastic client selection in federated learning to reduce representation misalignment and improve generalization on heterogeneous data.
FedFrozen improves stability in heterogeneous federated Transformer training by warming up the full model then freezing the attention kernel (query/key) while optimizing the value block under a fixed kernel.
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.
Benchmark of federated learning plus knowledge distillation for point cloud classification reveals that label-free distillation objectives are required for student accuracy to reflect federated teacher quality rather than proxy labels.
FedInit uses reverse personalized initialization in FL to reduce client drift effects, showing via excess risk that inconsistency impacts generalization error more than optimization error.
citing papers explorer
-
BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation
BESplit mitigates non-IID bias in split federated learning via evidential aggregation, bias-compensated client pairing, and dual-teacher distillation, outperforming prior methods on five benchmarks.
-
Towards the Next Frontier of LLMs, Training on Private Data: A Cross-Domain Benchmark for Federated Fine-Tuning
Federated PEFT on LLMs across healthcare and finance datasets performs close to centralized training and beats isolated local training under non-IID conditions.
-
Fed3D: Federated 3D Object Detection
Fed3D is a federated 3D object detection system using local-global class-aware loss for heterogeneity and prompt modules for low-bandwidth communication, claiming better performance than prior methods on limited local data.
-
Enhancing Federated Quadruplet Learning: Stochastic Client Selection and Embedding Stability Analysis
FedQuad uses quadruplet constraints and stochastic client selection in federated learning to reduce representation misalignment and improve generalization on heterogeneous data.
-
FedFrozen: Two-Stage Federated Optimization via Attention Kernel Freezing
FedFrozen improves stability in heterogeneous federated Transformer training by warming up the full model then freezing the attention kernel (query/key) while optimizing the value block under a fixed kernel.
-
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.
-
Benchmarking Federated Learning and Knowledge Distillation for Point Cloud Classification
Benchmark of federated learning plus knowledge distillation for point cloud classification reveals that label-free distillation objectives are required for student accuracy to reflect federated teacher quality rather than proxy labels.
-
Rethinking the Personalized Relaxed Initialization in the Federated Learning: Consistency and Generalization
FedInit uses reverse personalized initialization in FL to reduce client drift effects, showing via excess risk that inconsistency impacts generalization error more than optimization error.