论文标题
Boba：拜占庭式企业联合学习与标签偏斜
BOBA: Byzantine-Robust Federated Learning with Label Skewness
论文作者
论文摘要
在联合学习中，大多数现有的强大聚合规则（AGRS）在IID设置中拜占庭式攻击，在该设置中，将客户数据视为独立且分布相同。在本文中，我们解决了标签偏斜度，这是一个更现实，更具挑战性的非IID设置，每个客户只能访问一些类别的数据。在这种情况下，最先进的AGR遭受了选择偏见的困扰，从而导致特定类别的性能下降；由于诚实客户梯度的差异增加，他们也更容易受到拜占庭攻击的影响。为了解决这些局限性，我们提出了一种名为Boba的高效两阶段方法。从理论上讲，我们证明了Boba具有最佳顺序的误差的收敛性。我们的经验评估表明，与各种基准相比，与各种模型和数据集之间的出色无偏见和鲁棒性。我们的代码可在https://github.com/baowenxuan/boba上找到。
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 .
