Large scale collaboration with autonomy: Decentralized data ICA
Large scale collaboration with autonomy: Decentralized data ICA
复制标题
DOI：
10.1109/mlsp.2015.7324344
复制
发表时间：
2015-11
期刊：
影响因子：
--
通讯作者：
Bradley T. Baker;Rogers F. Silva;V. Calhoun;A. Sarwate;S. Plis
中科院分区：
文献类型：
--
作者：
Bradley T. Baker;Rogers F. Silva;V. Calhoun;A. Sarwate;S. Plis
协作研究系统的数据共享可能无法使用在集中式数据中心收集和存储数据的当代架构。研究小组通常希望在本地控制他们的数据，但也愿意共享数据以进行协作。这可能源于研究文化以及隐私问题。为了充分利用这些聚合的大型数据集的潜力，我们希望工具能够在不传输数据的情况下执行联合分析。理想情况下，这些分析将具有与当前基于团队的研究结构相似的性能和易用性。在本文中，我们设计，实现和评估一个分散的数据独立成分分析（伊卡），满足这些标准。我们验证了我们的方法对功能性磁共振成像（fMRI）数据的时间伊卡，这种方法只共享中间的统计数据，并可能适合通过差分隐私进一步的隐私保护。
Data sharing for collaborative research systems may not be able to use contemporary architectures that collect and store data in centralized data centers. Research groups often wish to control their data locally but are willing to share access to it for collaborations. This may stem from research culture as well as privacy concerns. To leverage the potential of these aggregated larger data sets, we would like tools that perform joint analyses without transmitting the data. Ideally, these analyses would have similar performance and ease of use as current team-based research structures. In this paper we design, implement, and evaluate a decentralized data independent component analysis (ICA) that meets these criteria. We validate our method on temporal ICA for functional magnetic resonance imaging (fMRI) data; this method shares only intermediate statistics and may be amenable to further privacy protections via differential privacy.