Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 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

Learning under Imitative Strategic Behavior with Unforeseeable Outcomes (2405.01797v2)

Published 3 May 2024 in cs.AI

Abstract: Machine learning systems have been widely used to make decisions about individuals who may behave strategically to receive favorable outcomes, e.g., they may genuinely improve the true labels or manipulate observable features directly to game the system without changing labels. Although both behaviors have been studied (often as two separate problems) in the literature, most works assume individuals can (i) perfectly foresee the outcomes of their behaviors when they best respond; (ii) change their features arbitrarily as long as it is affordable, and the costs they need to pay are deterministic functions of feature changes. In this paper, we consider a different setting and focus on imitative strategic behaviors with unforeseeable outcomes, i.e., individuals manipulate/improve by imitating the features of those with positive labels, but the induced feature changes are unforeseeable. We first propose a Stackelberg game to model the interplay between individuals and the decision-maker, under which we examine how the decision-maker's ability to anticipate individual behavior affects its objective function and the individual's best response. We show that the objective difference between the two can be decomposed into three interpretable terms, with each representing the decision-maker's preference for a certain behavior. By exploring the roles of each term, we theoretically illustrate how a decision-maker with adjusted preferences may simultaneously disincentivize manipulation, incentivize improvement, and promote fairness. Such theoretical results provide a guideline for decision-makers to inform better and socially responsible decisions in practice.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. The strategic perceptron. In Proceedings of the 22nd ACM Conference on Economics and Computation, pages 6–25, 2021.
  2. On classification of strategic agents who can both game and improve. arXiv preprint arXiv:2203.00124, 2022a.
  3. Setting fair incentives to maximize improvement. arXiv preprint arXiv:2203.00134, 2022b.
  4. Multiagent evaluation mechanisms. Proceedings of the AAAI Conference on Artificial Intelligence, 34:1774–1781, 2020.
  5. Albert Bandura. Social learning through imitation. 1962.
  6. Albert Bandura. Social learning theory of aggression. Journal of communication, pages 12–29, 1978.
  7. Fairness and Machine Learning: Limitations and Opportunities. 2019.
  8. Transparency, detection and imitation in strategic classification. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pages 67–73, 2022.
  9. Gaming helps! learning from strategic interactions in natural dynamics. In International Conference on Artificial Intelligence and Statistics, pages 1234–1242, 2021.
  10. Information discrepancy in strategic learning. In International Conference on Machine Learning, pages 1691–1715, 2022.
  11. Best response regression. In Advances in Neural Information Processing Systems, 2017.
  12. The role of randomness and noise in strategic classification. CoRR, abs/2005.08377, 2020.
  13. Estimating and penalizing induced preference shifts in recommender systems. In International Conference on Machine Learning, pages 2686–2708. PMLR, 2022.
  14. Strategic recourse in linear classification. CoRR, abs/2011.00355, 2020a.
  15. Learning strategy-aware linear classifiers. Advances in Neural Information Processing Systems, 33:15265–15276, 2020b.
  16. Strategic classification from revealed preferences. In Proceedings of the 2018 ACM Conference on Economics and Computation, page 55–70, 2018.
  17. Strategic classification with graph neural networks, 2022.
  18. Incentivizing truthfulness through audits in strategic classification. In Proceedings of the AAAI Conference on Artificial Intelligence, number 6, pages 5347–5354, 2021.
  19. Certifying and removing disparate impact. In proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining, pages 259–268, 2015.
  20. Equalizing recourse across groups, 2019.
  21. Maximizing welfare with incentive-aware evaluation mechanisms. arXiv preprint arXiv:2011.01956, 2020.
  22. Strategic classification. In Proceedings of the 2016 ACM Conference on Innovations in Theoretical Computer Science, page 111–122, 2016a.
  23. Equality of opportunity in supervised learning. In Advances in Neural Information Processing Systems, 2016b.
  24. Performative power. In Advances in Neural Information Processing Systems, 2022.
  25. Strategic instrumental variable regression: Recovering causal relationships from strategic responses. In International Conference on Machine Learning, pages 8502–8522, 2022.
  26. On the long-term impact of algorithmic decision policies: Effort unfairness and feature segregation through social learning. In 36th International Conference on Machine Learning, pages 2692–2701, 2019.
  27. Causal strategic classification: A tale of two shifts, 2023.
  28. How to learn when data reacts to your model: Performative gradient descent. In Proceedings of the 38th International Conference on Machine Learning, pages 4641–4650, 2021.
  29. Alternative microfoundations for strategic classification. In Proceedings of the 38th International Conference on Machine Learning, pages 4687–4697, 2021.
  30. Incentive mechanisms for strategic classification and regression problems. In Proceedings of the 23rd ACM Conference on Economics and Computation, page 760–790, 2022.
  31. Performative federated learning: A solution to model-dependent and heterogeneous distribution shifts. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 12938–12946, 2024.
  32. A survey of algorithmic recourse: contrastive explanations and consequential recommendations. ACM Computing Surveys, 55(5):1–29, 2022.
  33. How do classifiers induce agents to invest effort strategically? page 1–23, 2020.
  34. Learning losses for strategic classification. arXiv preprint arXiv:2203.13421, 2022.
  35. Generalized strategic classification and the case of aligned incentives. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, pages 12593–12618, 2022.
  36. Delayed impact of fair machine learning. In International Conference on Machine Learning, pages 3150–3158. PMLR, 2018.
  37. The disparate equilibria of algorithmic decision making when individuals invest rationally. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, pages 381–391, 2020.
  38. Strategic ranking. In Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, pages 2489–2518, 2022.
  39. Learning under concept drift: A review. IEEE Transactions on Knowledge and Data Engineering, 31(12):2346–2363, 2018.
  40. Strategic classification is causal modeling in disguise. In Proceedings of the 37th International Conference on Machine Learning, 2020.
  41. Performative prediction. In Proceedings of the 37th International Conference on Machine Learning, pages 7599–7609, 2020.
  42. Unintended selection: Persistent qualification rate disparities and interventions. Advances in Neural Information Processing Systems, pages 26053–26065, 2021.
  43. From predictions to decisions: Using lookahead regularization. In Advances in Neural Information Processing Systems, pages 4115–4126, 2020.
  44. Causal strategic linear regression. In Proceedings of the 37th International Conference on Machine Learning, ICML’20, 2020.
  45. Omer Talha. Cheating is rampant on gre at home, 2024. URL https://brightlinkprep.com/cheating-is-rampant-on-gre-at-home/#:~:text=As%20I%20write%20this%2C%20test,seems%20to%20be%20taking%20notice.
  46. Linear models are robust optimal under strategic behavior. In Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, volume 130 of Proceedings of Machine Learning Research, pages 2584–2592, 13–15 Apr 2021.
  47. Optimal decision making under strategic behavior, 2019.
  48. Discovering optimal scoring mechanisms in causal strategic prediction, 2023.
  49. Fairness in learning-based sequential decision algorithms: A survey. In Handbook of Reinforcement Learning and Control, pages 525–555. 2021.
  50. Group retention when using machine learning in sequential decision making: the interplay between user dynamics and fairness. Advances in Neural Information Processing Systems, 32, 2019.
  51. Long-term impacts of fair machine learning. ergonomics in design, 28(3):7–11, 2020a.
  52. How do fair decisions fare in long-term qualification? In Advances in Neural Information Processing Systems, pages 18457–18469, 2020b.
  53. Fairness interventions as (Dis)Incentives for strategic manipulation. In Proceedings of the 39th International Conference on Machine Learning, pages 26239–26264, 2022.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Tian Xie (77 papers)
  2. Zhiqun Zuo (5 papers)
  3. Mohammad Mahdi Khalili (22 papers)
  4. Xueru Zhang (31 papers)
Citations (2)
View on Semantic Scholar

Summary

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

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

Tweets