arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.08290cs.LGcs.CV
收藏

用于联邦肿瘤分割挑战的鲁棒学习协议

Robust Learning Protocol for Federated Tumor Segmentation Challenge

IBM Research Europe(IBM欧洲研究院);IBM Research(IBM研究院)

Ambrish Rawat, Giulio Zizzo, Swanand Kadhe, Jonathan P. Epperlein, Stefano Braghin

摘要:

在这项工作中,我们设计了强大而有效的学习协议,用于协调联合肿瘤分割挑战(FeTS 2022)的联邦学习(FL)过程。为FeTS设置启用FL具有挑战性,主要是由于协作者之间的数据异构性和培训的通信成本。为了应对这些挑战,我们提出了鲁棒学习协议(RoLePRO),它是服务器端自适应优化(例如,服务器端Adam)和明智的参数(权重)聚集方案(例如,自适应加权聚合)。RoLePRO采用两阶段的方法,第一阶段由香草联邦平均组成,而第二阶段由一个明智的聚合方案组成,该方案使用复杂的重新加权,所有这些都在服务器上存在自适应优化算法。我们从广泛的实验中获得见解,以调整这两个阶段的学习率。

英文摘要:

In this work, we devise robust and efficient learning protocols for orchestrating a Federated Learning (FL) process for the Federated Tumor Segmentation Challenge (FeTS 2022). Enabling FL for FeTS setup is challenging mainly due to data heterogeneity among collaborators and communication cost of training. To tackle these challenges, we propose Robust Learning Protocol (RoLePRO) which is a combination of server-side adaptive optimisation (e.g., server-side Adam) and judicious parameter (weights) aggregation schemes (e.g., adaptive weighted aggregation). RoLePRO takes a two-phase approach, where the first phase consists of vanilla Federated Averaging, while the second phase consists of a judicious aggregation scheme that uses a sophisticated reweighting, all in the presence of an adaptive optimisation algorithm at the server. We draw insights from extensive experimentation to tune learning rates for the two phases.

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。

↑