arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.01792cs.LGcs.CVcs.MAstat.ML
收藏

我们能推广和分布私人表示学习吗?

Can we Generalize and Distribute Private Representation Learning?

Department of ECE Carnegie Mellon University(卡内基梅隆大学电气与计算机工程系)

Sheikh Shams Azam, Taejin Kim, Seyyedali Hosseinalipour, Carlee Joe-Wong, Saurabh Bagchi, Christopher Brinton

摘要:

我们研究的问题,学习表示,是私人的,但信息,即,提供有关“盟友”目标的信息,同时隐藏敏感的“对手”属性。我们提出了排除-包含生成对抗网络(EIGAN),这是一种通用的私有表示学习(PRL)架构,与现有的PRL解决方案不同,它考虑了多个盟友和对手属性。虽然集中聚合的数据集是大多数PRL技术的先决条件,但现实世界中的数据通常被孤立在多个分布式节点上,由于隐私问题,这些节点不愿意共享原始数据。我们通过开发D-EIGAN来解决这个实际约束,D-EIGAN是第一个分布式PRL方法,它在每个节点学习表示而不传输源数据。我们从理论上分析了最佳EIGAN和D-EIGAN编码器下对手的行为以及盟友和对手任务之间的依赖关系对优化目标的影响。我们在各种数据集上的实验证明了EIGAN在性能,鲁棒性和可扩展性方面的优势。特别是,EIGAN的性能优于以前的最先进的显着准确率(47%的提高),并且D-EIGAN的性能在不同的网络设置下始终与EIGAN相当。

英文摘要:

We study the problem of learning representations that are private yet informative, i.e., provide information about intended "ally" targets while hiding sensitive "adversary" attributes. We propose Exclusion-Inclusion Generative Adversarial Network (EIGAN), a generalized private representation learning (PRL) architecture that accounts for multiple ally and adversary attributes unlike existing PRL solutions. While centrally-aggregated dataset is a prerequisite for most PRL techniques, data in real-world is often siloed across multiple distributed nodes unwilling to share the raw data because of privacy concerns. We address this practical constraint by developing D-EIGAN, the first distributed PRL method that learns representations at each node without transmitting the source data. We theoretically analyze the behavior of adversaries under the optimal EIGAN and D-EIGAN encoders and the impact of dependencies among ally and adversary tasks on the optimization objective. Our experiments on various datasets demonstrate the advantages of EIGAN in terms of performance, robustness, and scalability. In particular, EIGAN outperforms the previous state-of-the-art by a significant accuracy margin (47% improvement), and D-EIGAN's performance is consistently on par with EIGAN under different network settings.

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。

↑