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:2411.12377 , year=
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
Foundation model priors amplify worst-client disparity under extreme federated heterogeneity, creating a fairness paradox where larger models perform worse for disadvantaged clients.
FeDa4Fair is a new library and benchmark for creating federated datasets with heterogeneous client-level biases to standardize evaluation of fairness methods in federated learning.
AlignFed introduces a multi-stage semantic alignment mechanism for asynchronous federated fine-tuning of LLMs to mitigate model drift, client drift, and aggregation unfairness in heterogeneous edge environments.
Entropy regularization of probabilistic gates improves test performance and sparsity recovery in scarce-data federated learning over Fed-IHT and FedAvg pruning.
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.
Task2Vec-based unsupervised metrics of client embedding cohesion, dispersion, and density correlate strongly with final federated learning performance across multiple datasets and heterogeneity levels.
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.
-
When More Parameters Hurt: Foundation Model Priors Amplify Worst-Client Disparity Under Extreme Federated Heterogeneity
Foundation model priors amplify worst-client disparity under extreme federated heterogeneity, creating a fairness paradox where larger models perform worse for disadvantaged clients.
-
FeDa4Fair: Client-Level Federated Datasets for Fairness Evaluation
FeDa4Fair is a new library and benchmark for creating federated datasets with heterogeneous client-level biases to standardize evaluation of fairness methods in federated learning.
-
AlignFed: Alignment-Aware Asynchronous Federated Fine-Tuning for Large Language Models in Heterogeneous Edge Environments
AlignFed introduces a multi-stage semantic alignment mechanism for asynchronous federated fine-tuning of LLMs to mitigate model drift, client drift, and aggregation unfairness in heterogeneous edge environments.
-
Entropy-Regularized Probabilistic Gates for Sparse Model Discovery in Scarce-Data Federated Learning
Entropy regularization of probabilistic gates improves test performance and sparsity recovery in scarce-data federated learning over Fed-IHT and FedAvg pruning.
-
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.
-
Task2vec Readiness: Diagnostics for Federated Learning from Pre-Training Embeddings
Task2Vec-based unsupervised metrics of client embedding cohesion, dispersion, and density correlate strongly with final federated learning performance across multiple datasets and heterogeneity levels.