Interpretable collaborative data analysis on distributed data
Interpretable collaborative data analysis on distributed data
复制标题
DOI：
10.1016/j.eswa.2021.114891
复制
发表时间：
2021-04-10
影响因子：
8.5
通讯作者：
Sakurai, Tetsuya
中科院分区：
文献类型：
--
作者：
Imakura, Akira;Inaba, Hiroaki;Sakurai, Tetsuya
本文提出了一种可解释的非模型共享协作数据分析方法作为联合学习系统，该方法是一种用于分析分布式数据的新兴技术。由于隐私和机密性问题，分析分布式数据在许多应用程序（例如医学，金融和制造）中至关重要。此外，获得的模型的解释性在联合学习系统的实际应用中起着重要作用。通过集中中间表示，这些中间表示是由每个方分别构建的，提出的方法获得了可解释的模型，可以实现协作分析，而无需揭示本地各方之间分布的单个数据和学习模型。数值实验表明，所提出的方法比单个分析获得更好的识别性能，并且与人工和现实世界中的集中分析相当。
This paper proposes an interpretable non-model sharing collaborative data analysis method as a federated learning system, which is an emerging technology for analyzing distributed data. Analyzing distributed data is essential in many applications, such as medicine, finance, and manufacturing, due to privacy and confidentiality concerns. In addition, interpretability of the obtained model plays an important role in the practical applications of federated learning systems. By centralizing intermediate representations, which are individually constructed by each party, the proposed method obtains an interpretable model, achieving collaborative analysis without revealing the individual data and learning models distributed between local parties. Numerical experiments indicate that the proposed method achieves better recognition performance than individual analysis and comparable performance to centralized analysis for both artificial and real-world problems.