arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2506.04071cs.LGcs.CV
收藏

基于最优传输的域对齐作为联邦学习预处理步骤

Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning

Florida International University(佛罗里达国际大学)

Luiz Manella Pereira, M. Hadi Amini

AI总结:

本文提出一种基于最优传输和Wasserstein重心的联邦学习预处理算法,通过将各边缘设备数据投影到统一目标RGB空间来缓解数据集不平衡,在CIFAR-10上以更少通信轮次实现更高泛化性能。

摘要:

联邦学习(FL)是机器学习的一个子领域,它避免将本地数据共享给中央服务器,从而可以增强隐私性和可扩展性。无法整合数据会导致一个独特的问题,称为数据集不平衡,即网络中的智能体对所试图学习预测的标签没有同等的表示。在联邦学习中,融合具有不平衡数据集的本地训练模型可能会降低全局模型聚合的性能,并降低更新后的本地模型质量以及分布式智能体决策的准确性。在这项工作中,我们引入了一种基于最优传输的预处理算法,该算法通过最小化边缘设备上数据的分布差异来对齐数据集。我们通过在计算通道级平均值时利用 Wasserstein 重心来实现这一目标。这些重心被收集在一个可信的中央服务器中,在那里它们共同生成一个目标 RGB 空间。通过将我们的数据集投影到这个目标空间,我们在全局层面上最小化了分布差异,由于最小化了样本间的方差,这促进了学习过程。我们在 CIFAR-10 数据集上展示了所提出方法的能力,表明其能够在更少的通信轮次中达到更高的泛化程度。

英文摘要:

Federated learning (FL) is a subfield of machine learning that avoids sharing local data with a central server, which can enhance privacy and scalability. The inability to consolidate data leads to a unique problem called dataset imbalance, where agents in a network do not have equal representation of the labels one is trying to learn to predict. In FL, fusing locally-trained models with unbalanced datasets may deteriorate the performance of global model aggregation, and reduce the quality of updated local models and the accuracy of the distributed agents' decisions. In this work, we introduce an Optimal Transport-based preprocessing algorithm that aligns the datasets by minimizing the distributional discrepancy of data along the edge devices. We accomplish this by leveraging Wasserstein barycenters when computing channel-wise averages. These barycenters are collected in a trusted central server where they collectively generate a target RGB space. By projecting our dataset towards this target space, we minimize the distributional discrepancy on a global level, which facilitates the learning process due to a minimization of variance across the samples. We demonstrate the capabilities of the proposed approach over the CIFAR-10 dataset, where we show its capability of reaching higher degrees of generalization in fewer communication rounds.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑