Document Open Access Logo

Incentivized Collaboration in Active Learning

Authors Lee Cohen, Han Shao

PDF
Thumbnail PDF

File

LIPIcs.FORC.2024.2.pdf
  • Filesize: 0.74 MB
  • 20 pages

Document Identifiers

Author Details

Lee Cohen
  • Stanford University, CA, USA
Han Shao
  • Toyota Technological Institute of Chicago, IL, USA

Funding

This work was supported in part by the National Science Foundation under grants 2212968 and 2216899, by the Simons Foundation under the Simons Collaboration on the Theory of Algorithmic Fairness, by the Defense Advanced Research Projects Agency under cooperative agreement HR00112020003. The views expressed in this work do not necessarily reflect the position or the policy of the Government and no official endorsement should be inferred. Approved for public release; distribution is unlimited.

Acknowledgements

We would like to thank Avrim Blum for several useful discussions.

Cite AsGet BibTex

Lee Cohen and Han Shao. Incentivized Collaboration in Active Learning. In 5th Symposium on Foundations of Responsible Computing (FORC 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 295, pp. 2:1-2:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
https://doi.org/10.4230/LIPIcs.FORC.2024.2

Abstract

In collaborative active learning, where multiple agents try to learn labels from a common hypothesis, we introduce an innovative framework for incentivized collaboration. Here, rational agents aim to obtain labels for their data sets while keeping label complexity at a minimum. We focus on designing (strict) individually rational (IR) collaboration protocols, ensuring that agents cannot reduce their expected label complexity by acting individually. We first show that given any optimal active learning algorithm, the collaboration protocol that runs the algorithm as is over the entire data is already IR. However, computing the optimal algorithm is NP-hard. We therefore provide collaboration protocols that achieve (strict) IR and are comparable with the best known tractable approximation algorithm in terms of label complexity.

Subject Classification

ACM Subject Classification
  • Social and professional topics → Computing / technology policy
Keywords
  • pool-based active learning
  • individual rationality
  • incentives
  • Bayesian
  • collaboration

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
    0
    Metadata Views

Related Versions

References

  1. Itai Ashlagi and Alvin E. Roth. Individual rationality and participation in large scale, multi-hospital kidney exchange. In Proceedings 12th ACM Conference on Electronic Commerce (EC-2011), 2011. Google Scholar
  2. Nicolas Aussel, Sophie Chabridon, and Yohan Petetin. Combining federated and active learning for communication-efficient distributed failure prediction in aeronautics. arXiv preprint arXiv:2001.07504, 2020. Google Scholar
  3. Jackie Baek and Vivek F. Farias. Fair exploration via axiomatic bargaining. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, pages 22034-22045, 2021. Google Scholar
  4. Gal Bahar, Omer Ben-Porat, Kevin Leyton-Brown, and Moshe Tennenholtz. Fiduciary bandits. In International Conference on Machine Learning, 2019. Google Scholar
  5. Gal Bahar, Rann Smorodinsky, and Moshe Tennenholtz. Economic recommendation systems: One page abstract. In Proceedings of the 2016 ACM Conference on Economics and Computation, EC, page 757, 2016. Google Scholar
  6. Gal Bahar, Rann Smorodinsky, and Moshe Tennenholtz. Social learning and the innkeeper’s challenge. In Proceedings of the 2019 ACM Conference on Economics and Computation, EC '19, page 153–170, New York, NY, USA, 2019. Association for Computing Machinery. URL: https://doi.org/10.1145/3328526.3329569.
  7. Kiarash Banihashem, MohammadTaghi Hajiaghayi, Suho Shin, and Aleksandrs Slivkins. Bandit social learning: Exploration under myopic behavior, 2023. URL: https://arxiv.org/abs/2302.07425.
  8. Omer Ben-Porat and Rotem Torkan. Learning with exposure constraints in recommendation systems. In Proceedings of the ACM Web Conference 2023, WWW '23, 2023. Google Scholar
  9. Avrim Blum, Ioannis Caragiannis, Nika Haghtalab, Ariel D. Procaccia, Eviatar B. Procaccia, and Rohit Vaish. Opting into optimal matchings. In Proceedings of the Twenty-Eighth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA '17, page 2351–2363, USA, 2017. Society for Industrial and Applied Mathematics. Google Scholar
  10. Avrim Blum and Paul Gölz. Incentive-compatible kidney exchange in a slightly semi-random model. In EC '21: The 22nd ACM Conference on Economics and Computation, Budapest, Hungary, July 18-23, 2021. ACM, 2021. Google Scholar
  11. Avrim Blum, Nika Haghtalab, Richard Lanas Phillips, and Han Shao. One for one, or all for all: Equilibria and optimality of collaboration in federated learning. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event, 2021. Google Scholar
  12. Avrim Blum, Nika Haghtalab, Ariel D Procaccia, and Mingda Qiao. Collaborative pac learning. In I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017. URL: https://proceedings.neurips.cc/paper_files/paper/2017/file/186a157b2992e7daed3677ce8e9fe40f-Paper.pdf.
  13. Avrim Blum and Thodoris Lykouris. Advancing Subgroup Fairness via Sleeping Experts. In Thomas Vidick, editor, 11th Innovations in Theoretical Computer Science Conference (ITCS 2020), volume 151 of Leibniz International Proceedings in Informatics (LIPIcs), pages 55:1-55:24, Dagstuhl, Germany, 2020. Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik. URL: https://doi.org/10.4230/LIPIcs.ITCS.2020.55.
  14. Avrim Blum and Yishay Mansour. Kidney exchange and endless paths: On the optimal use of an altruistic donor. CoRR, abs/2010.01645, 2020. URL: https://arxiv.org/abs/2010.01645.
  15. David Buchfuhrer, Shaddin Dughmi, Hu Fu, Robert Kleinberg, Elchanan Mossel, Christos H. Papadimitriou, Michael Schapira, Yaron Singer, and Christopher Umans. Inapproximability for vcg-based combinatorial auctions. In Proceedings of the Twenty-First Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 2010, Austin, Texas, USA, January 17-19, 2010. SIAM, 2010. Google Scholar
  16. Romain Camilleri, Andrew Wagenmaker, Jamie Morgenstern, Lalit Jain, and Kevin Jamieson. Fair active learning in low-data regimes. CoRR, abs/2312.08559, 2023. URL: https://doi.org/10.48550/ARXIV.2312.08559.
  17. Romain Camilleri, Andrew Wagenmaker, Jamie H. Morgenstern, Lalit Jain, and Kevin G. Jamieson. Active learning with safety constraints. In NeurIPS, 2022. Google Scholar
  18. Venkatesan T Chakaravarthy, Vinayaka Pandit, Sambuddha Roy, Pranjal Awasthi, and Mukesh Mohania. Decision trees for entity identification: Approximation algorithms and hardness results. In Proceedings of the twenty-sixth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems, pages 53-62, 2007. Google Scholar
  19. Yeon-Koo Che and Johannes Hörner. Optimal design for social learning, 2013. Google Scholar
  20. Lee Cohen and Yishay Mansour. Optimal algorithm for bayesian incentive-compatible exploration. In Proceedings of the 2019 ACM Conference on Economics and Computation, EC '19, page 135–151, New York, NY, USA, 2019. Association for Computing Machinery. URL: https://doi.org/10.1145/3328526.3329581.
  21. Sanjoy Dasgupta. Analysis of a greedy active learning strategy. Advances in neural information processing systems, 17, 2004. Google Scholar
  22. John P. Dickerson, Ariel D. Procaccia, and Tuomas Sandholm. Failure-aware kidney exchange. Manag. Sci., 2019. Google Scholar
  23. Kate Donahue, Alexandra Chouldechova, and Krishnaram Kenthapadi. Human-algorithm collaboration: Achieving complementarity and avoiding unfairness. In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, FAccT '22, page 1639–1656, New York, NY, USA, 2022. Association for Computing Machinery. URL: https://doi.org/10.1145/3531146.3533221.
  24. Kate Donahue and Jon Kleinberg. Model-sharing games: Analyzing federated learning under voluntary participation. Proceedings of the AAAI Conference on Artificial Intelligence, 2021. Google Scholar
  25. Kate Donahue and Jon Kleinberg. Fairness in model-sharing games. In Proceedings of the ACM Web Conference 2023, WWW '23, page 3775–3783, New York, NY, USA, 2023. Association for Computing Machinery. URL: https://doi.org/10.1145/3543507.3583483.
  26. Kate Donahue and Jon M. Kleinberg. Optimality and stability in federated learning: A game-theoretic approach. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, 2021. Google Scholar
  27. Federico Echenique and Siddharth Prasad. Incentive compatible active learning. arXiv preprint arXiv:1911.05171, 2019. Google Scholar
  28. Yoav Freund, H. Sebastian Seung, Eli Shamir, and Naftali Tishby. Selective sampling using the query by committee algorithm. Mach. Learn., 1997. Google Scholar
  29. Daniel Golovin, Andreas Krause, and Debajyoti Ray. Near-optimal bayesian active learning with noisy observations. Advances in Neural Information Processing Systems, 23, 2010. Google Scholar
  30. Steve Hanneke. Theory of disagreement-based active learning. Foundations and Trends® in Machine Learning, 7, 2014. Google Scholar
  31. Moritz Hardt, Nimrod Megiddo, Christos Papadimitriou, and Mary Wootters. Strategic classification. In Proceedings of the 2016 ACM conference on innovations in theoretical computer science, pages 111-122, 2016. Google Scholar
  32. Nicole Immorlica, Jieming Mao, Aleksandrs Slivkins, and Zhiwei Steven Wu. Bayesian exploration with heterogeneous agents. In The World Wide Web Conference, WWW '19, page 751–761, New York, NY, USA, 2019. Association for Computing Machinery. URL: https://doi.org/10.1145/3308558.3313649.
  33. Nicole Immorlica, Jieming Mao, Aleksandrs Slivkins, and Zhiwei Steven Wu. Incentivizing exploration with selective data disclosure. In Proceedings of the 21st ACM Conference on Economics and Computation, EC '20, page 647–648, New York, NY, USA, 2020. Association for Computing Machinery. URL: https://doi.org/10.1145/3391403.3399487.
  34. S Rao Kosaraju, Teresa M Przytycka, and Ryan Borgstrom. On an optimal split tree problem. In Algorithms and Data Structures: 6th International Workshop, WADS’99 Vancouver, Canada, August 11-14, 1999 Proceedings, pages 157-168. Springer, 2002. Google Scholar
  35. Ilan Kremer, Yishay Mansour, and Motty Perry. Implementing the "wisdom of the crowd". J. of Political Economy, 122:988-1012, October 2014. Preliminary version appeared in ACM Conf. on Economics and Computation, 2014. Google Scholar
  36. Lingjuan Lyu, Xinyi Xu, Qian Wang, and Han Yu. Collaborative Fairness in Federated Learning, pages 189-204. Springer International Publishing, Cham, 2020. URL: https://doi.org/10.1007/978-3-030-63076-8_14.
  37. Yishay Mansour, Aleksandrs Slivkins, and Vasilis Syrgkanis. Bayesian incentive-compatible bandit exploration. In Proceedings of the Sixteenth ACM Conference on Economics and Computation, EC '15, pages 565-582, 2015. Google Scholar
  38. Yishay Mansour, Aleksandrs Slivkins, Vasilis Syrgkanis, and Zhiwei Steven Wu. Bayesian exploration: Incentivizing exploration in bayesian games. In Proceedings of the 2016 ACM Conference on Economics and Computation, EC '16, pages 661-661, New York, NY, USA, 2016. ACM. URL: https://doi.org/10.1145/2940716.2940755.
  39. Yishay Mansour, Aleksandrs Slivkins, and Zhiwei Steven Wu. Competing Bandits: Learning Under Competition. In Innovations in Theoretical Computer Science Conference (ITCS 2018), 2018. Google Scholar
  40. Ronza Najjar-Debbiny, Naomi Gronich, Gabriel Weber, Johad Khoury, Maisam Amar, Nili Stein, Lee Hilary Goldstein, and Walid Saliba. Effectiveness of Paxlovid in Reducing Severe Coronavirus Disease 2019 and Mortality in High-Risk Patients. Clinical Infectious Diseases, 2022. Google Scholar
  41. Alvin E. Roth, Tayfun Sönmez, and M. Utku Ünver. Kidney Exchange*. The Quarterly Journal of Economics, 2004. Google Scholar
  42. Mark Sellke and Aleksandrs Slivkins. The price of incentivizing exploration: A characterization via thompson sampling and sample complexity. In Proceedings of the 22nd ACM Conference on Economics and Computation, EC '21, page 795–796, New York, NY, USA, 2021. Association for Computing Machinery. URL: https://doi.org/10.1145/3465456.3467549.
  43. Shai Shalev-Shwartz and Shai Ben-David. Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press, 2014. Google Scholar
  44. Jie Shen, Nan Cui, and Jing Wang. Metric-fair active learning. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, Proceedings of Machine Learning Research, 2022. Google Scholar
  45. Pengcheng Shen, Chunguang Li, and Zhaoyang Zhang. Distributed active learning. IEEE Access, 4:2572-2579, 2016. Google Scholar
  46. Max Simchowitz and Aleksandrs Slivkins. Exploration and incentives in reinforcement learning, 2023. URL: https://arxiv.org/abs/2103.00360.
  47. A. Slivkins. Introduction to Multi-Armed Bandits. Foundations and Trends in Machine Learning Series. Now Publishers, 2019. URL: https://books.google.com/books?id=6ViCzQEACAAJ.
  48. Aleksandrs Slivkins. Incentivizing exploration via information asymmetry. ACM Crossroads, 24(1):38-41, 2017. URL: https://doi.org/10.1145/3123744.
  49. Xinran Wang, Qi Le, Ahmad Faraz Khan, Jie Ding, and Ali Anwar. A framework for incentivized collaborative learning. arXiv preprint arXiv:2305.17052, 2023. Google Scholar
  50. Zhepei Wei, Chuanhao Li, Haifeng Xu, and Hongning Wang. Incentivized communication for federated bandits. arXiv preprint arXiv:2309.11702, 2023. Google Scholar
  51. Xinyi Xu, Zhaoxuan Wu, Arun Verma, Chuan Sheng Foo, and Bryan Kian Hsiang Low. FAIR: fair collaborative active learning with individual rationality for scientific discovery. In International Conference on Artificial Intelligence and Statistics, 25-27 April 2023, Palau de Congressos, Valencia, Spain, 2023. Google Scholar
  52. Hanrui Zhang, Yu Cheng, and Vincent Conitzer. Efficient algorithms for planning with participation constraints. In Proceedings of the 23rd ACM Conference on Economics and Computation, EC '22, page 1121–1140, New York, NY, USA, 2022. Association for Computing Machinery. URL: https://doi.org/10.1145/3490486.3538280.
© 2023-2024 Schloss Dagstuhl – LZI GmbH Imprint Privacy Contact