Alliance Makes Difference? Maximizing Social Welfare in Cross-Silo Federated Learning

dc.contributor.authorChen, Jianan
dc.contributor.authorHu, Qin
dc.contributor.authorJiang, Honglu
dc.contributor.departmentComputer and Information Science, Purdue School of Science
dc.date.accessioned2024-12-17T19:23:45Z
dc.date.available2024-12-17T19:23:45Z
dc.date.issued2024-02
dc.description.abstractAs one of the typical settings of Federated Learning (FL), cross-silo FL allows organizations to jointly train an optimal Machine Learning (ML) model. In this case, some organizations may try to obtain the global model without contributing their local training power, lowering the social welfare. In this article, we model the interactions among organizations in cross-silo FL as a public goods game and theoretically prove that there exists a social dilemma where the maximum social welfare is not achieved in Nash equilibrium. To overcome this dilemma, we employ the Multi-player Multi-action Zero-Determinant (MMZD) strategy to maximize the social welfare. With the help of the MMZD, an individual organization can unilaterally control the social welfare without extra cost. Since the MMZD strategy can be adopted by all organizations, we further study the case of multiple organizations jointly adopting the MMZD strategy to form an MMZD Alliance (MMZDA). We prove that the MMZDA strategy can strengthen the control of the maximum social welfare. Experimental results validate that the MMZD strategy is effective in obtaining the maximum social welfare and the MMZDA can achieve a larger maximum value.
dc.eprint.versionAuthor's manuscript
dc.identifier.citationChen, J., Hu, Q., & Jiang, H. (2024). Alliance Makes Difference? Maximizing Social Welfare in Cross-Silo Federated Learning. IEEE Transactions on Vehicular Technology, 73(2), 2786–2798. IEEE Transactions on Vehicular Technology. https://doi.org/10.1109/TVT.2023.3320550
dc.identifier.urihttps://hdl.handle.net/1805/45108
dc.language.isoen
dc.publisherIEEE
dc.relation.isversionof10.1109/TVT.2023.3320550
dc.relation.journalIEEE Transactions on Vehicular Technology
dc.rightsPublisher Policy
dc.sourceArXiv
dc.subjectfederated learning
dc.subjectpublic goods game
dc.subjectzero-determinant strategy
dc.subjectsocial welfare
dc.titleAlliance Makes Difference? Maximizing Social Welfare in Cross-Silo Federated Learning
dc.typeArticle
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Chen2024Alliance-AAM.pdf
Size:
2.29 MB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.04 KB
Format:
Item-specific license agreed upon to submission
Description: