arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.09856cs.LGcs.DCcs.GT
收藏

联邦学习中的贡献评估:审视当前方法

Contribution Evaluation in Federated Learning: Examining Current Approaches

Imperial College London(帝国理工学院);City University London(伦敦城市大学);Flashbots

Vasilis Siomos, Jonathan Passerat-Palmbach

AI总结:

本文综述联邦学习中的贡献评估方法,提出新方法并在MNIST和CIFAR-10上基准测试,强调公平高效评估对FL主流采用的关键作用。

摘要:

联邦学习(FL)在实体希望协作训练模型同时保持对其数据的隐私和治理的场景中受到越来越多的关注。在FL中,拥有私有且可能异构的数据和计算资源的客户端共同训练一个通用模型,而原始数据从不离开其本地。相反,参与者通过共享本地模型更新来做出贡献,这些更新自然在质量上有所不同。定量评估这些贡献的价值被称为贡献评估(CE)问题。我们回顾了当前的CE方法,从底层数学框架到高效计算每个客户端的公平价值。此外,我们在MNIST和CIFAR-10上对一些最有前景的最先进方法以及我们引入的一种新方法进行了基准测试,以展示它们的差异。设计一个公平且高效的CE方法,虽然是整个FL系统设计中的一小部分,但对于FL的主流采用至关重要。

英文摘要:

Federated Learning (FL) has seen increasing interest in cases where entities want to collaboratively train models while maintaining privacy and governance over their data. In FL, clients with private and potentially heterogeneous data and compute resources come together to train a common model without raw data ever leaving their locale. Instead, the participants contribute by sharing local model updates, which, naturally, differ in quality. Quantitatively evaluating the worth of these contributions is termed the Contribution Evaluation (CE) problem. We review current CE approaches from the underlying mathematical framework to efficiently calculate a fair value for each client. Furthermore, we benchmark some of the most promising state-of-the-art approaches, along with a new one we introduce, on MNIST and CIFAR-10, to showcase their differences. Designing a fair and efficient CE method, while a small part of the overall FL system design, is tantamount to the mainstream adoption of FL.

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。

↑