Social-aware Federated Learning: Challenges and Opportunities in Collaborative Data Training

Abdul-Rasheed  Ottun; Pramod C.  Mane; Zhigang Yin; Souvik  Paul; Mohan Liyanage; Jason  Pridmore; Aaron Yi Ding; Rajesh Sharma; Petteri Nurmi; Huber Flores

doi:10.1109/MIC.2022.3219263

Social-aware Federated Learning: Challenges and Opportunities in Collaborative Data Training

Abdul-Rasheed Ottun, Pramod C. Mane, Zhigang Yin, Souvik Paul, Mohan Liyanage, Jason Pridmore, Aaron Yi Ding, Rajesh Sharma, Petteri Nurmi, Huber Flores

Department of Computer Science

Research output: Contribution to journal › Article › Scientific › peer-review

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.

Original language	English
Journal	IEEE Internet Computing
Volume	27
Issue number	2
Pages (from-to)	36-44
Number of pages	9
ISSN	1089-7801
DOIs	https://doi.org/10.1109/MIC.2022.3219263
Publication status	Published - Mar 2023
MoE publication type	A1 Journal article-refereed

Bibliographical note

© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”

Fields of Science

113 Computer and information sciences
516 Educational sciences

Access to Document

10.1109/MIC.2022.3219263Licence: CC BY-NC-ND

Social_Aware_Federated_Machine_Learning_IEEE_Internet_ComputingAccepted author manuscript, 2.63 MBLicence: Other
FeatureFinal published version, 1.38 MBLicence: CC BY-NC-ND

Foundations of Pervasive Sensing Systems
Nurmi, P. (Principal Investigator)
01/09/2021 → 31/08/2025
Project: Research Council of Finland: Academy Project

Cite this

@article{f64d3bcb841e41acafc3d7060553850f,

title = "Social-aware Federated Learning: Challenges and Opportunities in Collaborative Data Training",

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.",

keywords = "113 Computer and information sciences, 516 Educational sciences",

author = "Abdul-Rasheed Ottun and Mane, {Pramod C.} and Zhigang Yin and Souvik Paul and Mohan Liyanage and Jason Pridmore and Ding, {Aaron Yi} and Rajesh Sharma and Petteri Nurmi and Huber Flores",

note = "{\textcopyright} 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”",

year = "2023",

month = mar,

doi = "10.1109/MIC.2022.3219263",

language = "English",

volume = "27",

pages = "36--44",

journal = "IEEE Internet Computing",

issn = "1089-7801",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "2",

}

TY - JOUR

T1 - Social-aware Federated Learning: Challenges and Opportunities in Collaborative Data Training

AU - Ottun, Abdul-Rasheed

AU - Mane, Pramod C.

AU - Yin, Zhigang

AU - Paul, Souvik

AU - Liyanage, Mohan

AU - Pridmore, Jason

AU - Ding, Aaron Yi

AU - Sharma, Rajesh

AU - Nurmi, Petteri

AU - Flores, Huber

N1 - © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”

PY - 2023/3

Y1 - 2023/3

N2 - 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.

AB - 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.

KW - 113 Computer and information sciences

KW - 516 Educational sciences

U2 - 10.1109/MIC.2022.3219263

DO - 10.1109/MIC.2022.3219263

M3 - Article

SN - 1089-7801

VL - 27

SP - 36

EP - 44

JO - IEEE Internet Computing

JF - IEEE Internet Computing

IS - 2

ER -

Social-aware Federated Learning: Challenges and Opportunities in Collaborative Data Training

Abstract

Bibliographical note

Fields of Science

Access to Document

Projects

Foundations of Pervasive Sensing Systems

Cite this