Social-aware Federated Learning

Challenges and Opportunities in Collaborative Data Training

Journal article (2022)

Authors

Abdul Rasheed Ottun University of Tartu
Pramod C. Mane Indian Institute of Management Rohtak
Zhigang Yin University of Tartu
Souvik Paul University of Tartu
Mohan Liyanage University of Tartu
Jason Pridmore Erasmus Universiteit Rotterdam
Rajesh Sharma University of Tartu
Petteri Nurmi University of Helsinki
Huber Flores University of Tartu
Copyright: © 2022 Abdul Rasheed Ottun, Pramod C. Mane, Zhigang Yin, Souvik Paul, Mohan Liyanage, Jason Pridmore, Aaron Yi Ding, Rajesh Sharma, Petteri Nurmi, Huber Flores
DOI: https://doi.org/10.1109/MIC.2022.3219263
More Info
expand_more

Published Date

2022

Language

English

Abstract

Federated learning (FL) is a promising privacy-preserving solution to build powerful AI models. In many FL scenarios, such as healthcare or smart city monitoring, the user's devices may lack the required capabilities to collect suitable data, which limits their contributions to the global model. We contribute social-aware federated learning as a solution to boost the contributions of individuals by allowing outsourcing tasks to social connections. We identify key challenges and opportunities, and establish a research roadmap for the path forward. Through a user study with N = 30 participants, we study collaborative incentives for FL showing that social-aware collaborations can significantly boost the number of contributions to a global model provided that the right incentive structures are in place.