# BOBA: Byzantine-Robust Federated Learning with Label Skewness

arXiv: https://arxiv.org/abs/2208.12932 · HTML: https://mlsanity.com/paper/2208.12932/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 35 references that are in the map.
- First posted on arXiv 27 Aug 2022.

## Builds on (most cited first, 18 of 18)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates](https://mlsanity.com/paper/1803.01498/) (2018)
- [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020)
- [Local Model Poisoning Attacks to Byzantine-Robust Federated Learning](https://mlsanity.com/paper/1911.11815/) (2019)
- [A Little Is Enough: Circumventing Defenses For Distributed Learning](https://mlsanity.com/paper/1902.06156/) (2019)
- [Federated Multi-Task Learning under a Mixture of Distributions](https://mlsanity.com/paper/2108.10252/) (2021)
- [Privacy and Robustness in Federated Learning: Attacks and Defenses](https://mlsanity.com/paper/2012.06337/) (2020)
- [Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulation](https://mlsanity.com/paper/1903.03936/) (2019)
- [Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing](https://mlsanity.com/paper/2006.09365/) (2020)
- [FedMix: Approximation of Mixup under Mean Augmented Federated Learning](https://mlsanity.com/paper/2107.00233/) (2021)
- [Robust Federated Learning in a Heterogeneous Environment](https://mlsanity.com/paper/1906.06629/) (2019)
- [Federated Variance-Reduced Stochastic Gradient Descent with Robustness to Byzantine Attacks](https://mlsanity.com/paper/1912.12716/) (2019)
- [Federated Learning with Only Positive Labels](https://mlsanity.com/paper/2004.10342/) (2020)
- [FedDPGAN: Federated Differentially Private Generative Adversarial Networks Framework for the Detection of COVID-19 Pneumonia](https://mlsanity.com/paper/2104.12581/) (2021)
- [Byzantine-Robust Variance-Reduced Federated Learning over Distributed Non-i.i.d. Data](https://mlsanity.com/paper/2009.08161/) (2020)

## Built on by (most cited first, 7 of 7)

- [Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions](https://mlsanity.com/paper/2411.12377/) (2024)
- [BRFL: A Blockchain-based Byzantine-Robust Federated Learning Model](https://mlsanity.com/paper/2310.13403/) (2023)
- [Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework](https://mlsanity.com/paper/2502.00846/) (2025)
- [On the Gradient Heterogeneity Dynamics of Adversarially Robust Federated Regression](https://mlsanity.com/paper/2609.25705/) (2026)
- [FLTG: Byzantine-Robust Federated Learning via Angle-Based Defense and Non-IID-Aware Weighting](https://mlsanity.com/paper/2505.12851/) (2025)
- [Enhanced Byzantine-Robust Federated Learning Via Truncated-Quadratic Loss for Heterogeneous Data](https://mlsanity.com/paper/2607.10970/) (2026)
- [FUSE: Fairness-aware Update Screening against Byzantine Exploitation in q-Fair Federated Learning](https://mlsanity.com/paper/2610.20264/) (2026)

## 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 .