Towards Realistic Mechanisms That Incentivize Federated Participation and Contribution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bornstein, Marco, Bedi, Amrit Singh, Sahu, Anit Kumar, Khan, Furqan, Huang, Furong
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913358898266112
author Bornstein, Marco
Bedi, Amrit Singh
Sahu, Anit Kumar
Khan, Furqan
Huang, Furong
author_facet Bornstein, Marco
Bedi, Amrit Singh
Sahu, Anit Kumar
Khan, Furqan
Huang, Furong
contents Edge device participation in federating learning (FL) is typically studied through the lens of device-server communication (e.g., device dropout) and assumes an undying desire from edge devices to participate in FL. As a result, current FL frameworks are flawed when implemented in realistic settings, with many encountering the free-rider dilemma. In a step to push FL towards realistic settings, we propose RealFM: the first federated mechanism that (1) realistically models device utility, (2) incentivizes data contribution and device participation, (3) provably removes the free-rider dilemma, and (4) relaxes assumptions on data homogeneity and data sharing. Compared to previous FL mechanisms, RealFM allows for a non-linear relationship between model accuracy and utility, which improves the utility gained by the server and participating devices. On real-world data, RealFM improves device and server utility, as well as data contribution, by over 3 and 4 magnitudes respectively compared to baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2310_13681
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Towards Realistic Mechanisms That Incentivize Federated Participation and Contribution
Bornstein, Marco
Bedi, Amrit Singh
Sahu, Anit Kumar
Khan, Furqan
Huang, Furong
Computer Science and Game Theory
Computers and Society
Distributed, Parallel, and Cluster Computing
Machine Learning
Theoretical Economics
Edge device participation in federating learning (FL) is typically studied through the lens of device-server communication (e.g., device dropout) and assumes an undying desire from edge devices to participate in FL. As a result, current FL frameworks are flawed when implemented in realistic settings, with many encountering the free-rider dilemma. In a step to push FL towards realistic settings, we propose RealFM: the first federated mechanism that (1) realistically models device utility, (2) incentivizes data contribution and device participation, (3) provably removes the free-rider dilemma, and (4) relaxes assumptions on data homogeneity and data sharing. Compared to previous FL mechanisms, RealFM allows for a non-linear relationship between model accuracy and utility, which improves the utility gained by the server and participating devices. On real-world data, RealFM improves device and server utility, as well as data contribution, by over 3 and 4 magnitudes respectively compared to baselines.
title Towards Realistic Mechanisms That Incentivize Federated Participation and Contribution
topic Computer Science and Game Theory
Computers and Society
Distributed, Parallel, and Cluster Computing
Machine Learning
Theoretical Economics
url https://arxiv.org/abs/2310.13681