arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1812.03337cs.LGstat.ML
收藏

安全联邦迁移学习

Secure Federated Transfer Learning

WeBank(微众银行);Shanghai Jiao Tong University(上海交通大学);Hong Kong University of Science and Technology(香港科技大学)

Yang Liu, Yan Kang, Chaoping Xing, Tianjian Chen, Qiang Yang

摘要:

机器学习依赖于大量数据的可用性进行训练。然而,在现实中,大多数数据分散在不同的组织中,在许多法律和实际限制下无法轻松集成。在本文中,我们介绍了一种新的技术和框架,称为联邦迁移学习(FTL),以改善统计模型下的数据联邦。该联盟允许在不损害用户隐私的情况下共享知识,并使补充知识能够在网络中传输。因此,目标域方可以通过利用来自源域方的丰富标签来构建更灵活、更强大的模型。为了保证联邦下的FTL性能,提出了一种安全的传输交叉验证方法。该框架需要对现有模型结构进行最小的修改,并提供与非隐私保护方法相同的准确性。该框架非常灵活,可以有效地适应各种安全的多方机器学习任务。

英文摘要:

Machine learning relies on the availability of a vast amount of data for training. However, in reality, most data are scattered across different organizations and cannot be easily integrated under many legal and practical constraints. In this paper, we introduce a new technique and framework, known as federated transfer learning (FTL), to improve statistical models under a data federation. The federation allows knowledge to be shared without compromising user privacy, and enables complimentary knowledge to be transferred in the network. As a result, a target-domain party can build more flexible and powerful models by leveraging rich labels from a source-domain party. A secure transfer cross validation approach is also proposed to guard the FTL performance under the federation. The framework requires minimal modifications to the existing model structure and provides the same level of accuracy as the non-privacy-preserving approach. This framework is very flexible and can be effectively adapted to various secure multi-party machine learning tasks.

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。

↑