mlsanityData to 7 Oct 2026

BOBA: Byzantine-Robust Federated Learning with Label Skewness

arXiv 2208.12932 ↗First posted 27 Aug 2022cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

In federated learning, most existing robust aggregation rules (AGRs) combat Byzantine attacks in the IID setting, where client data is assumed to be independent and identically distributed. In this paper, we address label skewness, a more realistic and challenging non-IID setting, where each client only has access to a few classes of data. In this setting, state-of-the-art AGRs suffer from selection bias, leading to significant performance drop for particular classes; they are also more vulnerable to Byzantine attacks due to the increased variation among gradients of honest clients. To address these limitations, we propose an efficient two-stage method named BOBA. Theoretically, we prove the convergence of BOBA with an error of the optimal order. Our empirical evaluations demonstrate BOBA's superior unbiasedness and robustness across diverse models and datasets when compared to various baselines. Our code is available at https://github.com/baowenxuan/BOBA .

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 18 of its 35 references that are in the map. First posted on arXiv 27 Aug 2022.

Builds on

18 of 35 references.

References · 18

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  3. 2018Federated Learning with Non-IID Datacited by 1,099
  4. 2020Adaptive Federated Optimizationcited by 1,036
  5. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  6. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  7. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  8. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 285
  9. 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 189
  10. 2020Privacy and Robustness in Federated Learning: Attacks and Defensescited by 163
  11. 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 136
  12. 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 125
6 more
  1. 2021FedMix: Approximation of Mixup under Mean Augmented Federated Learningcited by 108
  2. 2019Robust Federated Learning in a Heterogeneous Environmentcited by 88
  3. 2019Federated Variance-Reduced Stochastic Gradient Descent with Robustness to Byzantine Attackscited by 79
  4. 2020Federated Learning with Only Positive Labelscited by 55
  5. 2021FedDPGAN: Federated Differentially Private Generative Adversarial Networks Framework for the Detection of COVID-19 Pneumoniacited by 22
  6. 2020Byzantine-Robust Variance-Reduced Federated Learning over Distributed Non-i.i.d. Datacited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 2; 2026: 2.

6 papers.

  1. 2024Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directionscited by 12
  2. 2023BRFL: A Blockchain-based Byzantine-Robust Federated Learning Modelcited by 2
  3. 2025Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Frameworkcited by 1
  4. 2025FLTG: Byzantine-Robust Federated Learning via Angle-Based Defense and Non-IID-Aware Weightingcited by 0
  5. 2026Enhanced Byzantine-Robust Federated Learning Via Truncated-Quadratic Loss for Heterogeneous Datacited by 0
  6. 2026On the Gradient Heterogeneity Dynamics of Adversarially Robust Federated Regressioncited by 0