Federated Machine Learning: Concept and Applications
This work tackles data privacy and accessibility issues for industries and organizations, but it is incremental as it builds on existing federated learning concepts.
The paper addresses the challenges of data isolation and privacy in AI by proposing a secure federated learning framework, which includes horizontal, vertical, and federated transfer learning, and suggests building data networks for knowledge sharing without compromising privacy.
Today's AI 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 allow knowledge to be shared without compromising user privacy.