Title: A General Differentially Private Learning Framework for Decentralized Data
Abstract:Decentralized consensus learning has been hugely successful that minimizing a finite sum of expected objectives over a network of agents. However, the local communication across neighbouring agents in the network may lead to the leakage of private information. To address this challenge, we propose a general differentially private (DP) learning framework that is applicable to direct and indirect communication networks without a central coordinator. We show that the proposed algorithm retains the performance guarantee in terms of generalization and finite sample performance. We investigate the impact of local privacy-preserving computation on the global DP guarantee. Further, we extend the discussion by adopting a new class of noise-adding DP mechanisms based on generalized Gaussian distributions to improve the utility-privacy trade-offs. Our numerical results demonstrate the effectiveness of our algorithm and its better performance over the state-of-the-art baseline methods in various decentralized settings.
报告题目:去中心化下保护数据隐私的学习框架
报告人:王亚飞(艾塞克斯大学)
报告时间:2022年12月9日17:00
报告地点:388-974-689
主办单位:beat365官方网站
报告对象:beat365官方网站及全校感兴趣的教师、研究生和本科生
内容摘要:去中心化学习通过极小化若干个服务器的损失总和受到广泛研究,但是服务器之间的信息传递会导致个人信息泄漏。我们提出一种可以保护数据隐私的学习框架,并且研究了所提算法的性质---泛化性,有限样本性质。此外,我们理论上给出了全局的隐私保护怎样受局部服务器的影响。考虑到所提算法的可行性,基于广义高斯分布,我们提出了一种新的加噪声的机制。
报告人简介:
王亚飞,英国University of Essex,Assistant Professor,博士生导师。主要研究方向是复杂数据分析特别是影像数据分析, 随机优化。多项研究成果发表在JMVA, CSDA、NeurIPS, AAAI等国际顶级期刊。