Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

User Strategization and Trustworthy Algorithms (2312.17666v1)

Published 29 Dec 2023 in cs.CY, cs.GT, cs.LG, and stat.ML

Abstract: Many human-facing algorithms -- including those that power recommender systems or hiring decision tools -- are trained on data provided by their users. The developers of these algorithms commonly adopt the assumption that the data generating process is exogenous: that is, how a user reacts to a given prompt (e.g., a recommendation or hiring suggestion) depends on the prompt and not on the algorithm that generated it. For example, the assumption that a person's behavior follows a ground-truth distribution is an exogeneity assumption. In practice, when algorithms interact with humans, this assumption rarely holds because users can be strategic. Recent studies document, for example, TikTok users changing their scrolling behavior after learning that TikTok uses it to curate their feed, and Uber drivers changing how they accept and cancel rides in response to changes in Uber's algorithm. Our work studies the implications of this strategic behavior by modeling the interactions between a user and their data-driven platform as a repeated, two-player game. We first find that user strategization can actually help platforms in the short term. We then show that it corrupts platforms' data and ultimately hurts their ability to make counterfactual decisions. We connect this phenomenon to user trust, and show that designing trustworthy algorithms can go hand in hand with accurate estimation. Finally, we provide a formalization of trustworthiness that inspires potential interventions.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (55)
  1. “Learning auctions with robust incentive guarantees” In Advances in neural information processing systems 32 proceedings.neurips.cc, 2019
  2. Kareem Amin, Afshin Rostamizadeh and Umar Syed “Learning prices for repeated auctions with strategic buyers” In Advances in neural information processing systems 26 proceedings.neurips.cc, 2013
  3. “Beyond accuracy: The role of mental models in human-AI team performance” In Proceedings of the AAAI Conference on Human Computation and Crowdsourcing 7 Association for the Advancement of Artificial Intelligence (AAAI), 2019, pp. 2–11
  4. “Investigating the relationship between AI and trust in human-AI collaboration” In Hawaii International Conference on System Sciences 2021 (HICSS-54) aisel.aisnet.org, 2021
  5. James Bergin and W Bentley MacLeod “Continuous Time Repeated Games” In International economic review 34.1 [Economics Department of the University of Pennsylvania, Wiley, Institute of SocialEconomic Research, Osaka University], 1993, pp. 21–37
  6. J Aislinn Bohren “Informational herding with model misspecification” In Journal of Economic Theory 163 Elsevier, 2016, pp. 222–247
  7. J Aislinn Bohren and Daniel N Hauser “Learning with heterogeneous misspecified models: Characterization and robustness” In Econometrica: journal of the Econometric Society 89.6 The Econometric Society, 2021, pp. 3025–3077
  8. Gavin Brown, Shlomi Hod and Iden Kalemaj “Performative Prediction in a Stateful World” In Proceedings of The 25th International Conference on Artificial Intelligence and Statistics 151, Proceedings of Machine Learning Research PMLR, 2022, pp. 6045–6061
  9. Michael Brückner, Christian Kanzow and Tobias Scheffer “Static prediction games for adversarial learning problems” Accessed: 2023-10-31 jmlr.org, https://www.jmlr.org/papers/volume13/brueckner12a/brueckner12a.pdf, 2012
  10. Lucian Busoniu, Robert Babuska and Bart De Schutter “A comprehensive survey of multiagent reinforcement learning” In IEEE transactions on systems, man and cybernetics. Part C, Applications and reviews: a publication of the IEEE Systems, Man, and Cybernetics Society 38.2 Institute of ElectricalElectronics Engineers (IEEE), 2008, pp. 156–172
  11. S H Cen, A Ilyas and A Madry “A Game-Theoretic Perspective on Trust in Recommendation” In NeurIPS Workshop on Responsible Decision Making in Dynamic Environments (RDD), 2022
  12. “Measuring Strategization in Recommendation: Users Adapt Their Behavior to Shape Future Content” In Preprint, 2023
  13. “Revenue-Incentive Tradeoffs in Dynamic Reserve Pricing” In Proceedings of the 38th International Conference on Machine Learning 139, Proceedings of Machine Learning Research PMLR, 2021, pp. 2601–2610
  14. “Strategic Classification from Revealed Preferences” In Proceedings of the 2018 ACM Conference on Economics and Computation, EC ’18 Ithaca, NY, USA: Association for Computing Machinery, 2018, pp. 55–70
  15. “Berk–Nash equilibrium: A framework for modeling agents with misspecified models” In Econometrica 84.3 Wiley Online Library, 2016, pp. 1093–1130
  16. “Trust Engineering for Human-AI Teams” In Proceedings of the Human Factors and Ergonomics Society … Annual Meeting Human Factors and Ergonomics Society. Meeting 63.1 SAGE Publications Inc, 2019, pp. 322–326
  17. Mira Frick, Ryota Iijima and Yuhta Ishii “Stability and robustness in misspecified learning models” Cowles Foundation Discussion Paper, 2020
  18. D Fudenberg, G Romanyuk and P Strack “Active learning with a misspecified prior” In Theoretical Economics Wiley Online Library, 2017
  19. Drew Fudenberg, Giacomo Lanzani and Philipp Strack “Limit points of endogenous misspecified learning” In Econometrica: journal of the Econometric Society 89.3 The Econometric Society, 2021, pp. 1065–1098
  20. Drew Fudenberg and David K Levine “Self-Confirming Equilibrium” In Econometrica: journal of the Econometric Society 61.3 [Wiley, Econometric Society], 1993, pp. 523–545
  21. “Strategic Classification in the Dark” In Proceedings of the 38th International Conference on Machine Learning 139, Proceedings of Machine Learning Research PMLR, 2021, pp. 3672–3681
  22. “Cooperative inverse reinforcement learning” In Proceedings of the 30th International Conference on Neural Information Processing Systems, NIPS’16 Barcelona, Spain: Curran Associates Inc., 2016, pp. 3916–3924
  23. “Learning in Stackelberg Games with Non-myopic Agents” In Proceedings of the 23rd ACM Conference on Economics and Computation, EC ’22 Boulder, CO, USA: Association for Computing Machinery, 2022, pp. 917–918
  24. Russell Hardin “Trust” Polity, 2006
  25. “Strategic Classification” In Proceedings of the 2016 ACM Conference on Innovations in Theoretical Computer Science, ITCS ’16 Cambridge, Massachusetts, USA: Association for Computing Machinery, 2016, pp. 111–122
  26. Andreas Haupt, Dylan Hadfield-Menell and Chara Podimata “Recommending to Strategic Users” In Foundations of Responsible Computing, 2023
  27. Keke Hou, Tingting Hou and Lili Cai “Exploring Trust in Human–AI Collaboration in the Context of Multiplayer Online Games” In Systems 11.5 Multidisciplinary Digital Publishing Institute, 2023, pp. 217
  28. “Subjective Equilibrium in Repeated Games” In Econometrica: journal of the Econometric Society 61.5 [Wiley, Econometric Society], 1993, pp. 1231–1240
  29. “Subjective games and equilibria” In Games and economic behavior 8.1, 1995, pp. 123–163
  30. “Incentive-Compatible Learning of Reserve Prices for Repeated Auctions” In Companion Proceedings of The 2019 World Wide Web Conference, WWW ’19 San Francisco, USA: Association for Computing Machinery, 2019, pp. 932–933
  31. “Investigating How Users Design Everyday Intelligent Systems in Use” In Proceedings of the 2023 ACM Designing Interactive Systems Conference, DIS ’23 Pittsburgh, PA, USA: Association for Computing Machinery, 2023, pp. 702–711
  32. Jon Kleinberg, Sendhil Mullainathan and Manish Raghavan “The Challenge of Understanding What Users Want: Inconsistent Preferences and Engagement Optimization” In Proceedings of the 23rd ACM Conference on Economics and Computation, EC ’22 Boulder, CO, USA: Association for Computing Machinery, 2022, pp. 29
  33. Roderick M Kramer “Trust and distrust in organizations: Emerging perspectives, enduring questions” In Annual review of psychology 50.1 Annual Reviews 4139 El Camino Way, PO Box 10139, Palo Alto, CA 94303-0139, USA, 1999, pp. 569–598
  34. “Generalized Strategic Classification and the Case of Aligned Incentives” In Proceedings of the 39th International Conference on Machine Learning 162, Proceedings of Machine Learning Research PMLR, 2022, pp. 12593–12618
  35. George J Mailath and Larry Samuelson “Repeated games and reputations: Long-Run relationships” New York, NY: Oxford University Press, 2006
  36. Aarian Marshall “Uber Changes Its Rules, and Drivers Adjust Their Strategies”, 2020 URL: https://www.wired.com/story/uber-changes-rules-drivers-adjust-strategies/
  37. “Mechanism Design via Differential Privacy” In 48th Annual IEEE Symposium on Foundations of Computer Science (FOCS’07) ieeexplore.ieee.org, 2007, pp. 94–103
  38. “Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming”, 2022 arXiv:2210.14306 [cs.SE]
  39. “Learning in Repeated Auctions” In Foundations and Trends® in Machine Learning 15.3 Now Publishers, 2022, pp. 176–334
  40. Helen Nissenbaum “Securing trust online: Wisdom or oxymoron” In BUL Rev. 81 HeinOnline, 2001, pp. 635
  41. Kobbi Nissim, Rann Smorodinsky and Moshe Tennenholtz “Approximately optimal mechanism design via differential privacy” In Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, ITCS ’12 Cambridge, Massachusetts: Association for Computing Machinery, 2012, pp. 203–213
  42. “Adaptive trust calibration for human-AI collaboration” In PloS one 15.2 journals.plos.org, 2020, pp. e0229132
  43. “Performative Prediction” In Proceedings of the 37th International Conference on Machine Learning 119, Proceedings of Machine Learning Research PMLR, 2020, pp. 7599–7609
  44. “On the Equilibria of Alternating Move Games” In Proceedings of the 2010 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), Proceedings Society for IndustrialApplied Mathematics, 2010, pp. 805–816
  45. Ignacio Siles, Luciana Valerio-Alfaro and Ariana Meléndez-Moran “Learning to like TikTok . . . and not: Algorithm awareness as process” In New Media & Society SAGE Publications, 2022, pp. 14614448221138973
  46. Ellen Simpson, Andrew Hamann and Bryan Semaan “How to Tame “Your” Algorithm: LGBTQ+ Users’ Domestication of TikTok” In Proc. ACM Hum.-Comput. Interact. 6.GROUP New York, NY, USA: Association for Computing Machinery, 2022, pp. 1–27
  47. Ming Tan “Multi-agent reinforcement learning: Independent vs. cooperative agents” In Proceedings of the tenth international conference on machine learning, 1993
  48. “From Human-Human Collaboration to Human-AI Collaboration: Designing AI Systems That Can Work Together with People” In Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems, CHI EA ’20 Honolulu, HI, USA: Association for Computing Machinery, 2020
  49. “Human-AI Collaboration in Data Science: Exploring Data Scientists’ Perceptions of Automated AI” In Proc. ACM Hum.-Comput. Interact. 3.CSCW New York, NY, USA: Association for Computing Machinery, 2019, pp. 1–24
  50. M Wu, S Amin and A Ozdaglar “Multi-agent Bayesian Learning with Adaptive Strategies: Convergence and Stability” In arXiv preprint arXiv:2010.09128 arxiv.org, 2020
  51. M Wu, S Amin and A Ozdaglar “Multi-agent Bayesian Learning with Best Response Dynamics: Convergence and Stability” In arXiv preprint arXiv:2109.00719 arxiv.org, 2021
  52. Lantao Yu, Jiaming Song and Stefano Ermon “Multi-Agent Adversarial Inverse Reinforcement Learning” In Proceedings of the 36th International Conference on Machine Learning 97, Proceedings of Machine Learning Research PMLR, 2019, pp. 7194–7201
  53. Kaiqing Zhang, Zhuoran Yang and Tamer Başar “Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms” In Handbook of Reinforcement Learning and Control Cham: Springer International Publishing, 2021, pp. 321–384
  54. ““An Ideal Human”: Expectations of AI Teammates in Human-AI Teaming” In Proc. ACM Hum.-Comput. Interact. 4.CSCW3 New York, NY, USA: Association for Computing Machinery, 2021, pp. 1–25
  55. “Who Leads and Who Follows in Strategic Classification?” In Advances in neural information processing systems 34 proceedings.neurips.cc, 2021, pp. 15257–15269
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Sarah H. Cen (12 papers)
  2. Andrew Ilyas (39 papers)
  3. Aleksander Madry (86 papers)
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now