IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2206.02786.html
   My bibliography  Save this paper

Impossibility of Collective Intelligence

Author

Listed:
  • Krikamol Muandet

Abstract

Democratization of AI involves training and deploying machine learning models across heterogeneous and potentially massive environments. Diversity of data opens up a number of possibilities to advance AI systems, but also introduces pressing concerns such as privacy, security, and equity that require special attention. This work shows that it is theoretically impossible to design a rational learning algorithm that has the ability to successfully learn across heterogeneous environments, which we decoratively call collective intelligence (CI). By representing learning algorithms as choice correspondences over a hypothesis space, we are able to axiomatize them with essential properties. Unfortunately, the only feasible algorithm compatible with all of the axioms is the standard empirical risk minimization (ERM) which learns arbitrarily from a single environment. Our impossibility result reveals informational incomparability between environments as one of the foremost obstacles for researchers who design novel algorithms that learn from multiple environments, which sheds light on prerequisites for success in critical areas of machine learning such as out-of-distribution generalization, federated learning, algorithmic fairness, and multi-modal learning.

Suggested Citation

  • Krikamol Muandet, 2022. "Impossibility of Collective Intelligence," Papers 2206.02786, arXiv.org.
  • Handle: RePEc:arx:papers:2206.02786
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2206.02786
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Sen, Amartya, 1993. "Internal Consistency of Choice," Econometrica, Econometric Society, vol. 61(3), pages 495-521, May.
    2. van Giffen, Benjamin & Herhausen, Dennis & Fahse, Tobias, 2022. "Overcoming the pitfalls and perils of algorithms: A classification of machine learning biases and mitigation methods," Journal of Business Research, Elsevier, vol. 144(C), pages 93-106.
    3. Satterthwaite, Mark Allen, 1975. "Strategy-proofness and Arrow's conditions: Existence and correspondence theorems for voting procedures and social welfare functions," Journal of Economic Theory, Elsevier, vol. 10(2), pages 187-217, April.
    4. Gibbard, Allan, 1973. "Manipulation of Voting Schemes: A General Result," Econometrica, Econometric Society, vol. 41(4), pages 587-601, July.
    5. Ashesh Rambachan & Jon Kleinberg & Jens Ludwig & Sendhil Mullainathan, 2020. "An Economic Perspective on Algorithmic Fairness," AEA Papers and Proceedings, American Economic Association, vol. 110, pages 91-95, May.
    6. Amartya K. Sen, 1971. "Choice Functions and Revealed Preference," The Review of Economic Studies, Review of Economic Studies Ltd, vol. 38(3), pages 307-317.
    Full references (including those not matched with items on IDEAS)

    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. John W. Patty & Elizabeth Maggie Penn, 2019. "A defense of Arrow’s independence of irrelevant alternatives," Public Choice, Springer, vol. 179(1), pages 145-164, April.
    2. Barbera, S. & Bossert, W. & Pattanaik, P.K., 2001. "Ranking Sets of Objects," Cahiers de recherche 2001-02, Centre interuniversitaire de recherche en économie quantitative, CIREQ.
    3. Federico Fioravanti & Iyad Rahwan & Fernando Abel Tohm'e, 2022. "Classes of Aggregation Rules for Ethical Decision Making in Automated Systems," Papers 2206.05160, arXiv.org, revised Jun 2023.
    4. Wesley H. Holliday & Eric Pacuit, 2023. "Split Cycle: a new Condorcet-consistent voting method independent of clones and immune to spoilers," Public Choice, Springer, vol. 197(1), pages 1-62, October.
    5. Ning Yu, 2015. "A quest for fundamental theorems of social choice," Social Choice and Welfare, Springer;The Society for Social Choice and Welfare, vol. 44(3), pages 533-548, March.
    6. Arlegi, Ricardo & Teschl, Miriam, 2022. "Pareto rationalizability by two single-peaked preferences," Mathematical Social Sciences, Elsevier, vol. 118(C), pages 1-11.
    7. Bock, Hans-Hermann & Day, William H. E. & McMorris, F. R., 1998. "Consensus rules for committee elections," Mathematical Social Sciences, Elsevier, vol. 35(3), pages 219-232, May.
    8. Marco LiCalzi, 2022. "Bipartite choices," Decisions in Economics and Finance, Springer;Associazione per la Matematica, vol. 45(2), pages 551-568, December.
    9. John C. McCabe-Dansted & Arkadii Slinko, 2006. "Exploratory Analysis of Similarities Between Social Choice Rules," Group Decision and Negotiation, Springer, vol. 15(1), pages 77-107, January.
    10. James Schummer, 1999. "Almost-dominant Strategy Implementation," Discussion Papers 1278, Northwestern University, Center for Mathematical Studies in Economics and Management Science.
    11. Aleskerov, Fuad & Karabekyan, Daniel & Sanver, M. Remzi & Yakuba, Vyacheslav, 2012. "On the manipulability of voting rules: The case of 4 and 5 alternatives," Mathematical Social Sciences, Elsevier, vol. 64(1), pages 67-73.
    12. Lirong Xia, 2020. "How Likely Are Large Elections Tied?," Papers 2011.03791, arXiv.org, revised Jul 2021.
    13. Dindar, Hayrullah & Lainé, Jean, 2017. "Manipulation of single-winner large elections by vote pairing," Economics Letters, Elsevier, vol. 161(C), pages 105-107.
    14. Brandt, Felix & Saile, Christian & Stricker, Christian, 2022. "Strategyproof social choice when preferences and outcomes may contain ties," Journal of Economic Theory, Elsevier, vol. 202(C).
    15. Souvik Roy & Soumyarup Sadhukhan, 2019. "A characterization of random min–max domains and its applications," Economic Theory, Springer;Society for the Advancement of Economic Theory (SAET), vol. 68(4), pages 887-906, November.
    16. Mizukami, Hideki & Saijo, Tatsuyoshi & Wakayama, Takuma, 2003. "Strategy-Proof Sharing," Working Papers 1170, California Institute of Technology, Division of the Humanities and Social Sciences.
    17. Bruno Frey, 2011. "Tullock challenges: happiness, revolutions, and democracy," Public Choice, Springer, vol. 148(3), pages 269-281, September.
    18. Donaldson, Jason & Piacentino, Giorgia & Malenko, Nadya, 2017. "Deadlock on the Board," CEPR Discussion Papers 12503, C.E.P.R. Discussion Papers.
    19. Takamiya, Koji, 2001. "Coalition strategy-proofness and monotonicity in Shapley-Scarf housing markets," Mathematical Social Sciences, Elsevier, vol. 41(2), pages 201-213, March.
    20. Freixas, Josep & Parker, Cameron, 2015. "Manipulation in games with multiple levels of output," Journal of Mathematical Economics, Elsevier, vol. 61(C), pages 144-151.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    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:2206.02786. 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.