Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Classification Under Strategic Self-Selection (2402.15274v2)

Published 23 Feb 2024 in cs.LG

Abstract: When users stand to gain from certain predictions, they are prone to act strategically to obtain favorable predictive outcomes. Whereas most works on strategic classification consider user actions that manifest as feature modifications, we study a novel setting in which users decide -- in response to the learned classifier -- whether to at all participate (or not). For learning approaches of increasing strategic awareness, we study the effects of self-selection on learning, and the implications of learning on the composition of the self-selected population. We then propose a differentiable framework for learning under self-selective behavior, which can be optimized effectively. We conclude with experiments on real data and simulated behavior that both complement our analysis and demonstrate the utility of our approach.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. A reductions approach to fair classification. In Dy, J. and Krause, A. (eds.), Proceedings of the 35th International Conference on Machine Learning, volume 80 of Proceedings of Machine Learning Research, pp.  60–69. PMLR, 10–15 Jul 2018.
  2. Alvarez, S. A. An exact analytical relation among recall, precision, and classification accuracy in information retrieval. Boston College, Boston, Technical Report BCCS-02-01, pp.  1–22, 2002.
  3. Transparency, detection and imitation in strategic classification. In Proceedings of the 31st International Joint Conference on Artificial Intelligence, IJCAI 2022, 2022.
  4. Information discrepancy in strategic learning. In International Conference on Machine Learning, pp.  1691–1715. PMLR, 2022.
  5. Modeling attrition in recommender systems with departing bandits. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pp.  6072–6079, 2022.
  6. Screening with disadvantaged agents. In 4th Symposium on Foundations of Responsible Computing, 2023.
  7. Multi stage screening: Enforcing fairness and maximizing efficiency in a pre-existing pipeline. In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, pp.  1178–1193, 2022.
  8. Static prediction games for adversarial learning problems. The Journal of Machine Learning Research, 13(1):2617–2654, 2012.
  9. Carroll, G. Robustness and separation in multidimensional screening. Econometrica, 85(2):453–488, 2017. doi: 10.3982/ECTA14165.
  10. Linear classifiers that encourage constructive adaptation. Transactions on Machine Learning Research, 2023.
  11. What makes a good fisherman? linear regression under self-selection bias. In Proceedings of the 55th Annual ACM Symposium on Theory of Computing, pp.  1699–1712, 2023.
  12. Sequential strategic screening. In International Conference on Machine Learning, pp.  6279–6295. PMLR, 2023.
  13. Sequential Screening. The Review of Economic Studies, 67(4):697–717, October 2000. ISSN 0034-6527. doi: 10.1111/1467-937X.00150.
  14. Stochastic optimization with decision-dependent distributions. Mathematics of Operations Research, 2022.
  15. Fairness through awareness. In Proceedings of the 3rd innovations in theoretical computer science conference, pp.  214–226, 2012.
  16. Strategic classification with graph neural networks. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023.
  17. Strategic classification in the dark. In International Conference on Machine Learning, pp.  3672–3681. PMLR, 2021.
  18. Strategic classification. In Proceedings of the 2016 ACM conference on innovations in theoretical computer science, pp.  111–122, 2016.
  19. Strategic apple tasting. In Advances in Neural Information Processing Systems, volume 36, 2023.
  20. Causal strategic classifiaction. In International Conference on Machine Learning. PMLR, 2023.
  21. Alternative microfoundations for strategic classification. In International Conference on Machine Learning, pp.  4687–4697. PMLR, 2021.
  22. Fair sequential selection using supervised learning models. Advances in Neural Information Processing Systems, 34:28144–28155, 2021.
  23. Koren, M. The gatekeeper effect: The implications of pre-screening, self-selection, and bias for hiring processes. arXiv preprint arXiv:2312.17167, 2023.
  24. Classification with strategically withheld data. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pp.  5514–5522, 2021.
  25. A Bias of Screening. American Economic Review: Insights, 1(3):343–56, September 2019. doi: 10.1257/AERI.20180578.
  26. Screening Dominance: A Comparison of Noisy Signals. American Economic Journal: Microeconomics, 2021. ISSN 1945-7669. doi: 10.1257/MIC.20200284.
  27. A survey on datasets for fairness-aware machine learning. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 12(3):e1452, 2022.
  28. Strategic classification with unknown user manipulations. In International Conference on Machine Learning. PMLR, 2023.
  29. Generalized strategic classification and the case of aligned incentives. In Proceedings of the 39th International Conference on Machine Learning (ICML), 2022.
  30. Plug-in performative optimization. arXiv preprint arXiv:2305.18728, 2023.
  31. Addressing bias in artificial intelligence: The current regulatory landscape (white paper). Technical report, Duke Law, 2023. URL https://www.thomsonreuters.com/en-us/posts/wp-content/uploads/sites/20/2023/08/Addressing-Bias-in-AI-Report.pdf?ref=blog.salesforceairesearch.com.
  32. Anticipating performativity by predicting from predictions. Advances in Neural Information Processing Systems, 35:31171–31185, 2022.
  33. Strategic classification is causal modeling in disguise. In International Conference on Machine Learning, pp.  6917–6926. PMLR, 2020.
  34. On the within-group fairness of screening classifiers. In Proceedings of the 40th International Conference on Machine Learning, pp.  26495–26516, 2023.
  35. On fairness and calibration. Advances in neural information processing systems, 30, 2017.
  36. One-shot strategic classification under unknown costs. arXiv preprint arXiv:2311.02761, 2023.
  37. Strategic classification under unknown personalized manipulation. In Advances in Neural Information Processing Systems, volume 36, 2023.
  38. PAC-learning for strategic classification. In International Conference on Machine Learning, pp.  9978–9988. PMLR, 2021.
  39. On calibration and out-of-domain generalization. Advances in neural information processing systems, 34:2215–2227, 2021.
  40. Improving screening processes via calibrated subset selection. In International Conference on Machine Learning, pp.  22702–22726. PMLR, 2022.
  41. Classification with few tests through self-selection. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pp.  5805–5812, 2021.
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