Incentive

World Wide Web

Process (computing)

Engineering

Microeconomics

Federated learning

Operating system

Economics

Computer science

Internet privacy

Information privacy

Mechanical engineering

Database

Work (physics)

Data science

Artificial intelligence

Personalization

Statistical model

Machine learning

Data modeling

Federated learning enables machine learning models to learn from private decentralized data without compromising privacy. The standard formulation of federated learning produces one shared model for all clients. Statistical heterogeneity due to non-IID distribution of data across devices often leads to scenarios where, for some clients, the local models trained solely on their private data perform better than the global shared model thus taking away their incentive to participate in the process. Several techniques have been proposed to personalize global models to work better for individual clients. This paper highlights the need for personalization and surveys recent research on this topic.

Survey of Personalization Techniques for Federated Learning