REVIEW 4 cited by
FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Federated learning aims to collaboratively train a strong global model by accessing users' locally trained models but not their own data. A crucial step is therefore to aggregate local models into a global model, which has been shown challenging when users have non-i.i.d. data. In this paper, we propose a novel aggregation algorithm named FedBE, which takes a Bayesian inference perspective by sampling higher-quality global models and combining them via Bayesian model Ensemble, leading to much robust aggregation. We show that an effective model distribution can be constructed by simply fitting a Gaussian or Dirichlet distribution to the local models. Our empirical studies validate FedBE's superior performance, especially when users' data are not i.i.d. and when the neural networks go deeper. Moreover, FedBE is compatible with recent efforts in regularizing users' model training, making it an easily applicable module: you only need to replace the aggregation method but leave other parts of your federated learning algorithm intact. Our code is publicly available at https://github.com/hongyouc/FedBE.
Forward citations
Cited by 4 Pith papers
-
FedBKD: Distilled Federated Learning to Embrace Gerneralization and Personalization on Non-IID Data
A data-free GAN plus bidirectional knowledge distillation between global and local models improves both personalization and generalization in non-IID federated classification.
-
FedMLAC: Mutual Learning Driven Heterogeneous Federated Audio Classification
FedMLAC couples personalized local audio models with a shared plug-in model via bidirectional knowledge distillation, plus layer-wise pruning aggregation, to jointly address data, model, and label heterogeneity in fed...
-
Federated Learning on Stochastic Neural Networks
A federated learning algorithm that trains local stochastic neural networks to capture both the true function and the noise in each client's data.
-
Robust Knowledge Distillation in Federated Learning: Counteracting Backdoor Attacks
RKD defends federated learning against backdoor attacks by clustering client updates with cosine similarity and HDBSCAN, selecting median-like models, and distilling their ensemble into the global model.
Discussion (0). Continue with ORCID to comment.