mlsanityData to 14 Oct 2026

Time Can Invalidate Algorithmic Recourse

arXiv 2410.08007 ↗First posted 10 Oct 2024cs.LG cs.CYcited by 8

Not on the map. Why?

Abstract (arXiv)

Algorithmic Recourse (AR) aims to provide users with actionable steps to overturn unfavourable decisions made by machine learning predictors. However, these actions often take time to implement (e.g., getting a degree can take years), and their effects may vary as the world evolves. Thus, it is natural to ask for recourse that remains valid in a dynamic environment. In this paper, we study the robustness of algorithmic recourse over time by casting the problem through the lens of causality. We demonstrate theoretically and empirically that (even robust) causal AR methods can fail over time, except in the -- unlikely -- case that the world is stationary. Even more critically, unless the world is fully deterministic, counterfactual AR cannot be solved optimally. To account for this, we propose a simple yet effective algorithm for temporal AR that explicitly accounts for time under the assumption of having access to an estimator approximating the stochastic process. Our simulations on synthetic and realistic datasets show how considering time produces more resilient solutions to potential trends in the data distribution.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 43 of its 88 references that are in the map. First posted on arXiv 10 Oct 2024.

Builds on

43 of 88 references.

References · 43

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  3. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  4. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
  5. 2018Actionable Recourse in Linear Classificationcited by 328
  6. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
  7. 2016Model-Agnostic Interpretability of Machine Learningcited by 219
  8. 2019Model-Agnostic Counterfactual Explanations for Consequential Decisionscited by 204
  9. 2020Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Reviewcited by 174
  10. 2017Fair Inference On Outcomescited by 144
  11. 2020Algorithmic recourse under imperfect causal knowledge: a probabilistic approachcited by 140
  12. 2021Counterfactual Explanations Can Be Manipulatedcited by 113
31 more
  1. 2021Towards Robust and Reliable Algorithmic Recoursecited by 102
  2. 2018'It's Reducing a Human Being to a Percentage'; Perceptions of Justice in Algorithmic Decisionscited by 91
  3. 2020On Counterfactual Explanations under Predictive Multiplicitycited by 74
  4. 2020On the Fairness of Causal Algorithmic Recoursecited by 70
  5. 2020Instance-based Counterfactual Explanations for Time Series Classificationcited by 64
  6. 2021On the Adversarial Robustness of Causal Algorithmic Recoursecited by 56
  7. 2020Counterfactual Explanations for Machine Learning on Multivariate Time Series Datacited by 49
  8. 2023Robust Counterfactual Explanations for Neural Networks With Probabilistic Guaranteescited by 45
  9. 2021Evaluating Robustness of Counterfactual Explanationscited by 41
  10. 2022Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recoursecited by 40
  11. 2018Human Perceptions of Fairness in Algorithmic Decision Making: A Case Study of Criminal Risk Predictioncited by 35
  12. 2022On the Robustness of Sparse Counterfactual Explanations to Adverse Perturbationscited by 32
  13. 2022On the Privacy Risks of Algorithmic Recoursecited by 32
  14. 2024Robust Counterfactual Explanations in Machine Learning: A Surveycited by 29
  15. 2023Self-Interpretable Time Series Prediction with Counterfactual Explanationscited by 24
  16. 2022On the Trade-Off between Actionable Explanations and the Right to be Forgottencited by 20
  17. 2022Achieving Long-Term Fairness in Sequential Decision Makingcited by 19
  18. 2021Conceptualising Contestability: Perspectives on Contesting Algorithmic Decisionscited by 18
  19. 2021Counterfactual Explanations as Interventions in Latent Spacecited by 18
  20. 2023Setting the Right Expectations: Algorithmic Recourse Over Timecited by 13
  21. 2023Distributionally Robust Recourse Actioncited by 12
  22. 2022Personalized Algorithmic Recourse with Preference Elicitationcited by 9
  23. 2023Endogenous Macrodynamics in Algorithmic Recoursecited by 9
  24. 2023Designing Long-term Group Fair Policies in Dynamical Systemscited by 9
  25. 2021BeFair: Addressing Fairness in the Banking Sectorcited by 8
  26. 2022Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesiscited by 8
  27. 2024Exploiting Preference Elicitation in Interactive and User-centered Algorithmic Recourse: An Initial Explorationcited by 8
  28. 2022Counterfactuals for the Futurecited by 5
  29. 2023On Minimizing the Impact of Dataset Shifts on Actionable Explanationscited by 3
  30. 2023The Importance of Time in Causal Algorithmic Recoursecited by 2
  31. 2024Towards Non-Adversarial Algorithmic Recoursecited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 6.

8 papers.

  1. 2025Performative Validity of Recourse Explanationscited by 8
  2. 2025Reinforcement Learning for Durable Algorithmic Recoursecited by 3
  3. 2026Fairness under uncertainty in sequential decisionscited by 2
  4. 2026From Universal to Individualized Actionability: Revisiting Personalization in Algorithmic Recoursecited by 1
  5. 2026How Supply Chain Dependencies Complicate Bias Measurement and Accountability Attribution in AI Hiring Applicationscited by 0
  6. 2026Algorithmic Recourse of In-Context Learning for Tabular Datacited by 0
  7. 2026Personalized Causal Recourse: A Human-In-The-Loop Approachcited by 0
  8. 2026Algorithmic Recourse Under Competitioncited by 0