2026-09-18T23:16:11Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1629772025-12-15T15:42:32Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Bates, Stephen
Wang, Yuxiao
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2025-10-06T17:37:49Z
2025-10-06T17:37:49Z
2025-05
2025-06-23T14:04:10.898Z
https://hdl.handle.net/1721.1/162977
In a collaborative learning scheme such as the federated learning model, each user benefits from the data contribution of others. Previous work shows that the federated learning protocol can incentivize users to contribute more than in the competitive equilibrium by penalizing deviations. However, a central controller with access to all the data may raise privacy concerns. In this work, we construct a decentralized collaborative protocol in which users share data without relying on a centralized controller. We then extend this protocol to a repeated game and analyze the competitive equilibrium behavior, along with strategies users can implement to foster collaboration in the repeated setting of the protocol. We provide a quantitative analysis of free-rider behavior under decentralized protocols and compare the amount of information collected with decentralized protocols against that in the centralized protocol.
M.Eng.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright retained by author(s)
https://rightsstatements.org/page/InC-EDU/1.0/
Incentivizing Data Contributions in Decentralized Collaborative Learning
Thesis
application/pdf
Master
Master of Engineering in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="e5b98250-b04c-4593-9eea-3a9fcd6038b8">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Incentivizing Data Contributions in Decentralized Collaborative Learning</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2025-05</PublicationDate>
<Authors>
<Author>
<DisplayName>Wang, Yuxiao</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>In a collaborative learning scheme such as the federated learning model, each user benefits from the data contribution of others. Previous work shows that the federated learning protocol can incentivize users to contribute more than in the competitive equilibrium by penalizing deviations. However, a central controller with access to all the data may raise privacy concerns. In this work, we construct a decentralized collaborative protocol in which users share data without relying on a centralized controller. We then extend this protocol to a repeated game and analyze the competitive equilibrium behavior, along with strategies users can implement to foster collaboration in the repeated setting of the protocol. We provide a quantitative analysis of free-rider behavior under decentralized protocols and compare the amount of information collected with decentralized protocols against that in the centralized protocol.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>