IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2207.04557.html
   My bibliography  Save this paper

Mechanisms that Incentivize Data Sharing in Federated Learning

Author

Listed:
  • Sai Praneeth Karimireddy
  • Wenshuo Guo
  • Michael I. Jordan

Abstract

Federated learning is typically considered a beneficial technology which allows multiple agents to collaborate with each other, improve the accuracy of their models, and solve problems which are otherwise too data-intensive / expensive to be solved individually. However, under the expectation that other agents will share their data, rational agents may be tempted to engage in detrimental behavior such as free-riding where they contribute no data but still enjoy an improved model. In this work, we propose a framework to analyze the behavior of such rational data generators. We first show how a naive scheme leads to catastrophic levels of free-riding where the benefits of data sharing are completely eroded. Then, using ideas from contract theory, we introduce accuracy shaping based mechanisms to maximize the amount of data generated by each agent. These provably prevent free-riding without needing any payment mechanism.

Suggested Citation

  • Sai Praneeth Karimireddy & Wenshuo Guo & Michael I. Jordan, 2022. "Mechanisms that Incentivize Data Sharing in Federated Learning," Papers 2207.04557, arXiv.org.
    • Handle: RePEc:arx:papers:2207.04557
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2207.04557
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Philippe Bich, 2006. "Some fixed point theorems for discontinuous mappings," Post-Print halshs-00119033, HAL.
    2. Philippe Bich, 2006. "Some fixed point theorems for discontinuous mappings," Cahiers de la Maison des Sciences Economiques b06066, Université Panthéon-Sorbonne (Paris 1).
    3. Charles I. Jones & Christopher Tonetti, 2020. "Nonrivalry and the Economics of Data," American Economic Review, American Economic Association, vol. 110(9), pages 2819-2858, September.
    4. Philippe Bich, 2006. "Some fixed point theorems for discontinuous mappings," Université Paris1 Panthéon-Sorbonne (Post-Print and Working Papers) halshs-00119033, HAL.
    5. Maskin, Eric, 1986. "The Existence of Equilibrium with Price-Setting Firms," American Economic Review, American Economic Association, vol. 76(2), pages 382-386, May.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Bingchen Wang & Zhaoxuan Wu & Fusheng Liu & Bryan Kian Hsiang Low, 2024. "Paid with Models: Optimal Contract Design for Collaborative Machine Learning," Papers 2412.11122, arXiv.org, revised Dec 2024.
    2. Alireza Fallah & Michael I. Jordan & Ali Makhdoumi & Azarakhsh Malekian, 2024. "On Three-Layer Data Markets," Papers 2402.09697, arXiv.org, revised Feb 2024.
    3. Marco Bornstein & Amrit Singh Bedi & Anit Kumar Sahu & Furqan Khan & Furong Huang, 2023. "Towards Realistic Mechanisms That Incentivize Federated Participation and Contribution," Papers 2310.13681, arXiv.org, revised May 2024.
    4. Baihe Huang & Sai Praneeth Karimireddy & Michael I. Jordan, 2023. "Evaluating and Incentivizing Diverse Data Contributions in Collaborative Learning," Papers 2306.05592, arXiv.org.
    5. Marco Bornstein & Amrit Singh Bedi & Abdirisak Mohamed & Furong Huang, 2024. "FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?," Papers 2405.13879, arXiv.org, revised Oct 2024.
    6. Jiajun Meng & Jing Chen & Dongfang Zhao & Lin Liu, 2024. "Federated Learning and Free-riding in a Competitive Market," Papers 2410.12723, arXiv.org.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Takao Fujimoto, 2013. "Fixed Point Theorems for Discontinuous Maps on a Non-convex Domain," Metroeconomica, Wiley Blackwell, vol. 64(3), pages 547-572, July.
    2. Roy Chowdhury, Prabal, 2008. "Bertrand-Edgeworth equilibrium with a large number of firms," International Journal of Industrial Organization, Elsevier, vol. 26(3), pages 746-761, May.
    3. Prabal Roy Chowdhury, 2004. "Bertrand-Edgeworth duopoly with linear costs: A tale of two paradoxes," Discussion Papers 04-13, Indian Statistical Institute, Delhi.
    4. Soeiro, Renato & Adrego Pinto, Alberto, 2019. "Social power as a solution to the Bertrand Paradox," MPRA Paper 94271, University Library of Munich, Germany.
    5. de Pedraza, Pablo & Vollbracht, Ian, 2020. "The Semicircular Flow of the Data Economy and the Data Sharing Laffer curve," GLO Discussion Paper Series 515, Global Labor Organization (GLO).
    6. Jacobs, Martin & Requate, Till, 2016. "Bertrand-Edgeworth markets with increasing marginal costs and voluntary trading: Experimental evidence," Economics Working Papers 2016-01, Christian-Albrechts-University of Kiel, Department of Economics.
    7. Chowdhury, Prabal Roy, 2003. "Bertrand-Edgeworth equilibrium large markets with non-manipulable residual demand," Economics Letters, Elsevier, vol. 79(3), pages 371-375, June.
    8. Long Chen & Yadong Huang & Shumiao Ouyang & Wei Xiong, 2021. "The Data Privacy Paradox and Digital Demand," Working Papers 2021-47, Princeton University. Economics Department..
    9. Feng, Wei & Sun, Shujun & Yuan, Hang, 2023. "Research on the efficiency of factor allocation in the pilot free trade zones," Economic Analysis and Policy, Elsevier, vol. 79(C), pages 727-745.
    10. Daron Acemoglu & Ali Makhdoumi & Azarakhsh Malekian & Asu Ozdaglar, 2022. "Too Much Data: Prices and Inefficiencies in Data Markets," American Economic Journal: Microeconomics, American Economic Association, vol. 14(4), pages 218-256, November.
    11. Ehsan Valavi & Joel Hestness & Newsha Ardalani & Marco Iansiti, 2022. "Time and the Value of Data," Papers 2203.09118, arXiv.org.
    12. Wang, Li & Wu, Yuhan & Huang, Zeyu & Wang, Yanan, 2024. "Big data application and corporate investment decisions: Evidence from A-share listed companies in China," International Review of Financial Analysis, Elsevier, vol. 94(C).
    13. Bergemann, Dirk & Ottaviani, Marco, 2021. "Information Markets and Nonmarkets," CEPR Discussion Papers 16459, C.E.P.R. Discussion Papers.
    14. Joao Montez & Nicolas Schutz, 2021. "All-Pay Oligopolies: Price Competition with Unobservable Inventory Choices [Extremal Equilibria of Oligopolistic Supergames]," The Review of Economic Studies, Review of Economic Studies Ltd, vol. 88(5), pages 2407-2438.
    15. Bianchi, Milo & Bouvard, Matthieu & Gomes, Renato & Rhodes, Andrew & Shreeti, Vatsala, 2023. "Mobile payments and interoperability: Insights from the academic literature," Information Economics and Policy, Elsevier, vol. 65(C).
    16. Catherine E. Tucker, 2023. "The Economics of Privacy: An Agenda," NBER Chapters, in: The Economics of Privacy, National Bureau of Economic Research, Inc.
    17. Zhou, Zhongsheng & Li, Zhuo & Du, Shanzhong & Cao, June, 2024. "Robot adoption and enterprise R&D manipulation: Evidence from China," Technological Forecasting and Social Change, Elsevier, vol. 200(C).
    18. Martin Beraja & David Y Yang & Noam Yuchtman, 2023. "Data-intensive Innovation and the State: Evidence from AI Firms in China," The Review of Economic Studies, Review of Economic Studies Ltd, vol. 90(4), pages 1701-1723.
    19. repec:ctc:serie1:def11 is not listed on IDEAS
    20. Chen, S. & Doerr, S. & Frost, J. & Gambacorta, L. & Shin, H.S., 2023. "The fintech gender gap," Journal of Financial Intermediation, Elsevier, vol. 54(C).

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2207.04557. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.