Research Area:  Machine Learning
Today’s artificial intelligence still faces two major challenges. One is that, in most industries, data exists in the form of isolated islands. The other is the strengthening of data privacy and security. We propose a possible solution to these challenges: secure federated learning. Beyond the federated-learning framework first proposed by Google in 2016, we introduce a comprehensive secure federated-learning framework, which includes horizontal federated learning, vertical federated learning, and federated transfer learning. We provide definitions, architectures, and applications for the federated-learning framework, and provide a comprehensive survey of existing works on this subject. In addition, we propose building data networks among organizations based on federated mechanisms as an effective solution to allowing knowledge to be shared without compromising user privacy.
Keywords:  
Author(s) Name:   Qiang Yang , Yang Liu, Tianjian Chen ,Yongxin Tong
Journal name:  ACM Transactions on Intelligent Systems and Technology
Conferrence name:  
Publisher name:  ACM
DOI:  10.1145/3298981
Volume Information:  Volume 10,Issue 2,March 2019, Article No.: 12,pp 1–19
Paper Link:   https://dl.acm.org/doi/10.1145/3298981