mlsanityData to 7 Oct 2026

Generating Counterfactual and Contrastive Explanations using SHAP

arXiv 1906.09293 ↗First posted 21 Jun 2019cs.LG cs.AI stat.MLcited by 23

Not on the map. Why?

Abstract (arXiv)

With the advent of GDPR, the domain of explainable AI and model interpretability has gained added impetus. Methods to extract and communicate visibility into decision-making models have become legal requirement. Two specific types of explanations, contrastive and counterfactual have been identified as suitable for human understanding. In this paper, we propose a model agnostic method and its systemic implementation to generate these explanations using shapely additive explanations (SHAP). We discuss a generative pipeline to create contrastive explanations and use it to further to generate counterfactual datapoints. This pipeline is tested and discussed on the IRIS, Wine Quality & Mobile Features dataset. Analysis of the results obtained follows.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 12; 2022: 5; 2023: 5; 2024: 0; 2025: 1.

23 papers.

Sort:

  1. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  2. 2021Contrastive Explanations for Model Interpretabilitycited by 75
  3. 2021Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applicationscited by 59
  4. 2022The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanationscited by 41
  5. 2021On the Complexity of SHAP-Score-Based Explanations: Tractability via Knowledge Compilation and Non-Approximability Resultscited by 32
  6. 2021Amortized Generation of Sequential Algorithmic Recourses for Black-box Modelscited by 24
  7. 2021Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Surveycited by 24
  8. 2021Counterfactual Shapley Additive Explanationscited by 22
  9. 2021A Framework and Benchmarking Study for Counterfactual Generating Methods on Tabular Datacited by 19
  10. 2022MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanationcited by 12
  11. 2021Feature Synergy, Redundancy, and Independence in Global Model Explanations using SHAP Vector Decompositioncited by 9
  12. 2022Interpretation of Black Box NLP Models: A Surveycited by 9
11 more
  1. 2021Evaluating the Correctness of Explainable AI Algorithms for Classificationcited by 8
  2. 2022Benchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Boxcited by 7
  3. 2023SAFE: Saliency-Aware Counterfactual Explanations for DNN-based Automated Driving Systemscited by 5
  4. 2021Causal versus Marginal Shapley Values for Robotic Lever Manipulation Controlled using Deep Reinforcement Learningcited by 4
  5. 2023Counterfactual Explainer Framework for Deep Reinforcement Learning Models Using Policy Distillationcited by 3
  6. 2022Policy Optimization with Sparse Global Contrastive Explanationscited by 2
  7. 2023Rectifying Group Irregularities in Explanations for Distribution Shiftcited by 1
  8. 2023CLIMAX: An exploration of Classifier-Based Contrastive Explanationscited by 1
  9. 2021Towards an Explanation Space to Align Humans and Explainable-AI Teamworkcited by 0
  10. 2023CEnt: An Entropy-based Model-agnostic Explainability Framework to Contrast Classifiers' Decisionscited by 0
  11. 2025An Explainable Gaussian Process Auto-encoder for Tabular Datacited by 0