Pith. sign in

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

arxiv 2009.01974 v4 pith:EQOWFL3S submitted 2020-09-04 cs.LG stat.ML

classification cs.LGstat.ML
keywords modelfedbemodelsusersaggregationbayesiandatafederated
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. FedBKD: Distilled Federated Learning to Embrace Gerneralization and Personalization on Non-IID Data

    cs.LG 2025-06 conditional novelty 5.0 of 10

    A data-free GAN plus bidirectional knowledge distillation between global and local models improves both personalization and generalization in non-IID federated classification.

  2. FedMLAC: Mutual Learning Driven Heterogeneous Federated Audio Classification

    cs.SD 2025-06 conditional novelty 5.0 of 10

    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...

  3. Federated Learning on Stochastic Neural Networks

    cs.LG 2025-06 conditional novelty 5.0 of 10

    A federated learning algorithm that trains local stochastic neural networks to capture both the true function and the noise in each client's data.

  4. Robust Knowledge Distillation in Federated Learning: Counteracting Backdoor Attacks

    cs.CR 2025-02 conditional novelty 4.0 of 10

    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.

Pith tools