mlsanityData to 7 Oct 2026

Synthesizing Action Sequences for Modifying Model Decisions

arXiv 1910.00057 ↗First posted 30 Sep 2019cs.AIcited by 22

Not on the map. Why?

Abstract (arXiv)

When a model makes a consequential decision, e.g., denying someone a loan, it needs to additionally generate actionable, realistic feedback on what the person can do to favorably change the decision. We cast this problem through the lens of program synthesis, in which our goal is to synthesize an optimal (realistically cheapest or simplest) sequence of actions that if a person executes successfully can change their classification. We present a novel and general approach that combines search-based program synthesis and test-time adversarial attacks to construct action sequences over a domain-specific set of actions. We demonstrate the effectiveness of our approach on a number of deep neural networks.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 2; 2023: 9; 2024: 5; 2025: 2.

22 papers.

Sort:

  1. 2021If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniquescited by 82
  2. 2021Amortized Generation of Sequential Algorithmic Recourses for Black-box Modelscited by 24
  3. 2021A Framework and Benchmarking Study for Counterfactual Generating Methods on Tabular Datacited by 19
  4. 2021Consequence-aware Sequential Counterfactual Generationcited by 17
  5. 2023Achieving Diversity in Counterfactual Explanations: a Review and Discussioncited by 11
  6. 2022Personalized Algorithmic Recourse with Preference Elicitationcited by 9
  7. 2023Generating collective counterfactual explanations in score-based classification via mathematical optimizationcited by 9
  8. 2022Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesiscited by 8
  9. 2024Exploiting Preference Elicitation in Interactive and User-centered Algorithmic Recourse: An Initial Explorationcited by 8
  10. 2023Feasible Recourse Plan via Diverse Interpolationcited by 6
  11. 2023Navigating Explanatory Multiverse Through Counterfactual Path Geometrycited by 5
  12. 2023Prediction without Preclusion: Recourse Verification with Reachable Setscited by 4
10 more
  1. 2024Trustworthy Actionable Perturbationscited by 3
  2. 2023Unveiling the Potential of Counterfactuals Explanations in Employabilitycited by 2
  3. 2024Perfect Counterfactuals in Imperfect Worlds: Modelling Noisy Implementation of Actions in Sequential Algorithmic Recoursecited by 2
  4. 2023Iterative Partial Fulfillment of Counterfactual Explanations: Benefits and Riskscited by 1
  5. 2024Learning Actionable Counterfactual Explanations in Large State Spacescited by 1
  6. 2023Learning impartial policies for sequential counterfactual explanations using Deep Reinforcement Learningcited by 0
  7. 2023Explainable History Distillation by Marked Temporal Point Processcited by 0
  8. 2024Cost-Adaptive Recourse Recommendation by Adaptive Preference Elicitationcited by 0
  9. 2025Counterfactual optimization for fault prevention in complex wind energy systemscited by 0
  10. 2025Learning Marked Temporal Point Process Explanations based on Counterfactual and Factual Reasoningcited by 0