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 2206.01432cs.LGcs.DC
收藏

Wasserstein鲁棒联邦学习的推广

On the Generalization of Wasserstein Robust Federated Learning

The University of Sydney(悉尼大学);The Australian National University(澳大利亚国立大学)

Tung-Anh Nguyen, Tuan Dung Nguyen, Long Tan Le, Canh T. Dinh, Nguyen H. Tran

摘要:

在联邦学习中,参与的客户端通常拥有非独立身份识别。数据,对推广到看不见的分布构成了重大挑战。为了解决这个问题,我们提出了一个Wasserstein分布鲁棒优化计划称为WAFL。利用其对偶性,我们框架WAFL作为一个经验代理风险最小化问题,并解决它使用的局部SGD为基础的算法收敛保证。我们发现WAFL的鲁棒性比相关方法更一般,并且泛化界对Wasserstein球(模糊集)内的所有对抗分布都是鲁棒的。由于Wasserstein球的中心位置和半径可以适当地修改,WAFL不仅在鲁棒性方面,而且在领域自适应方面显示出其适用性。通过实证评估,我们证明了WAFL在非i.i.d.中的泛化能力优于vanilla FedAvg。在分布偏移设置下,比其他相关方法更稳健。此外,使用基准数据集,我们表明WAFL是能够推广到看不见的目标域。

英文摘要:

In federated learning, participating clients typically possess non-i.i.d. data, posing a significant challenge to generalization to unseen distributions. To address this, we propose a Wasserstein distributionally robust optimization scheme called WAFL. Leveraging its duality, we frame WAFL as an empirical surrogate risk minimization problem, and solve it using a local SGD-based algorithm with convergence guarantees. We show that the robustness of WAFL is more general than related approaches, and the generalization bound is robust to all adversarial distributions inside the Wasserstein ball (ambiguity set). Since the center location and radius of the Wasserstein ball can be suitably modified, WAFL shows its applicability not only in robustness but also in domain adaptation. Through empirical evaluation, we demonstrate that WAFL generalizes better than the vanilla FedAvg in non-i.i.d. settings, and is more robust than other related methods in distribution shift settings. Further, using benchmark datasets we show that WAFL is capable of generalizing to unseen target domains.

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。

↑