arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.06830cs.DC
收藏

联邦学习中用户贡献的探索性分析

An Exploratory Analysis on Users' Contributions in Federated Learning

Jiyue Huang, Rania Talbi, Zilong Zhao, Sara Boucchenak, Lydia Y. Chen, Stefanie Roos

摘要:

联邦学习是一种新兴的分布式协作学习范式,被当今的许多应用所采用,例如,键盘预测和对象识别。其核心原理是从大量用户数据中学习,同时通过设计保护数据隐私,因为协作用户只需要共享机器学习模型并将数据保存在本地。这类系统面临的主要挑战是激励用户贡献从其本地数据中训练出来的高质量模型。在本文中,我们的目标是回答如何激励识别(在)准确的本地模型从诚实和恶意用户,并感知其对联邦学习系统的模型准确性的影响。我们首先提出了一个彻底的调查两个对比的角度:激励机制来衡量本地模型的贡献诚实的用户,和恶意用户故意降低整体模型。我们进行模拟实验,经验证明,如果现有的贡献测量方案可以揭示恶意用户的低质量模型。我们的研究结果表明,在计算效率和有效性方面存在着明显的权衡测量方案提取恶意参与者的影响。最后,我们讨论了弹性贡献激励设计的研究方向。

英文摘要:

Federated Learning is an emerging distributed collaborative learning paradigm adopted by many of today's applications, e.g., keyboard prediction and object recognition. Its core principle is to learn from large amount of users data while preserving data privacy by design as collaborative users only need to share the machine learning models and keep data locally. The main challenge for such systems is to provide incentives to users to contribute high-quality models trained from their local data. In this paper, we aim to answer how well incentives recognize (in)accurate local models from honest and malicious users, and perceive their impacts on the model accuracy of federated learning systems. We first present a thorough survey on two contrasting perspectives: incentive mechanisms to measure the contribution of local models by honest users, and malicious users to deliberately degrade the overall model. We conduct simulation experiments to empirically demonstrate if existing contribution measurement schemes can disclose low-quality models from malicious users. Our results show there exists a clear tradeoff among measurement schemes in terms of the computational efficiency and effectiveness to distill the impact of malicious participants. We conclude this paper by discussing the research directions to design resilient contribution incentives.

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。

↑