Multi-agent incentive mechanism testbed simulator
Privacy regulation laws will likely continue to be widely reinforced and with stricter regulations. Federated Learning (FL) as an adoption for business will be beneficial in the long run as issues such as privacy preservation can be addressed while, continuing to be leveraging on big data. Therefore...
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project (FYP) |
Language: | English |
Published: |
Nanyang Technological University
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/138187 |
_version_ | 1826130296390549504 |
---|---|
author | Ng, Kang Loon |
author2 | Yu Han |
author_facet | Yu Han Ng, Kang Loon |
author_sort | Ng, Kang Loon |
collection | NTU |
description | Privacy regulation laws will likely continue to be widely reinforced and with stricter regulations. Federated Learning (FL) as an adoption for business will be beneficial in the long run as issues such as privacy preservation can be addressed while, continuing to be leveraging on big data. Therefore, there is a need for a proper framework to support FL in business to promote and sustain a healthy and long-lasting Federation. This is paramount to the growth of FL. FedGame serves as a valuable platform for the study of human participation behavior in the face of various incentive schemes. Users of the system will be able to experience FL participation as a data owner (business) and face decisions on participating in various Federations. Data collected on human decisions can be used and analyzed to formulate an optimal incentive scheme that encourages participation and commitment of high-quality data while still sustaining the Federation. |
first_indexed | 2024-10-01T07:54:09Z |
format | Final Year Project (FYP) |
id | ntu-10356/138187 |
institution | Nanyang Technological University |
language | English |
last_indexed | 2024-10-01T07:54:09Z |
publishDate | 2020 |
publisher | Nanyang Technological University |
record_format | dspace |
spelling | ntu-10356/1381872020-04-28T04:49:25Z Multi-agent incentive mechanism testbed simulator Ng, Kang Loon Yu Han School of Computer Science and Engineering han.yu@ntu.edu.sg Engineering::Computer science and engineering::Software Privacy regulation laws will likely continue to be widely reinforced and with stricter regulations. Federated Learning (FL) as an adoption for business will be beneficial in the long run as issues such as privacy preservation can be addressed while, continuing to be leveraging on big data. Therefore, there is a need for a proper framework to support FL in business to promote and sustain a healthy and long-lasting Federation. This is paramount to the growth of FL. FedGame serves as a valuable platform for the study of human participation behavior in the face of various incentive schemes. Users of the system will be able to experience FL participation as a data owner (business) and face decisions on participating in various Federations. Data collected on human decisions can be used and analyzed to formulate an optimal incentive scheme that encourages participation and commitment of high-quality data while still sustaining the Federation. Bachelor of Engineering (Computer Science) 2020-04-28T04:49:24Z 2020-04-28T04:49:24Z 2020 Final Year Project (FYP) https://hdl.handle.net/10356/138187 en application/pdf Nanyang Technological University |
spellingShingle | Engineering::Computer science and engineering::Software Ng, Kang Loon Multi-agent incentive mechanism testbed simulator |
title | Multi-agent incentive mechanism testbed simulator |
title_full | Multi-agent incentive mechanism testbed simulator |
title_fullStr | Multi-agent incentive mechanism testbed simulator |
title_full_unstemmed | Multi-agent incentive mechanism testbed simulator |
title_short | Multi-agent incentive mechanism testbed simulator |
title_sort | multi agent incentive mechanism testbed simulator |
topic | Engineering::Computer science and engineering::Software |
url | https://hdl.handle.net/10356/138187 |
work_keys_str_mv | AT ngkangloon multiagentincentivemechanismtestbedsimulator |