Counterfactual explanations mainly target to find the mimimum perturbation which changes the original prediction(Ususlly from an undesirable prediction to ideal one). The perturbation itself is a valid instance following the real data distribution as the training samples. It has broad applications, E.g., finance, education, health care ect. Specifically, what should I do to get the credit card approved if I received the rejection. This task can be viewed as extracting knowledge/solutions from the black-box models. It belongs to the instance-level explanation. Quite interesting to dive deeper!!!
The two use cases of counterfactual explanations:
Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications, Arxiv preprint 2021
A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence, IEEE Access 2021
Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI), Arxiv preprint 2020
Counterfactual Explanations for Machine Learning: A Review, Arxiv preprint 2020
A survey of algorithmic recourse: definitions, formulations, solutions, and prospects, Arxiv preprint 2020
On the computation of counterfactual explanations -- A survey, Arxiv preprint 2019
Issues with post-hoc counterfactual explanations: a discussion, ICML Workshop 2019
Counterfactuals in Explainable Artificial Intelligence (XAI): Evidence from Human Reasoning, IJCAI 2019
A Few Good Counterfactuals: Generating Interpretable, Plausible & Diverse Counterfactual Explanations, Arxiv preprint 2021
GeCo: Quality Counterfactual Explanations in Real Time, Arxiv preprint 2021
Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties, AISTATS 2021, code
FIMAP: Feature Importance by Minimal Adversarial Perturbation, AAAI 2021
Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Text, AAAI 2021
Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder, AAAI 2021
Counterfactual Explanations for Oblique Decision Trees: Exact, Efficient Algorithms, AAAI 2021
Ordered Counterfactual Explanation by Mixed-Integer Linear Optimization, AAAI 2021
Counterfactual Generative Networks, ICLR 2021, code
Learning "What-if" Explanations for Sequential Decision-Making, ICLR 2021
GRACE: Generating Concise and Informative Contrastive Sample to Explain Neural Network Model’s Prediction, KDD 2020 code
An ASP-Based Approach to Counterfactual Explanations for Classification, RuleML + PR 2020
DECE: Decision Explorer with Counterfactual Explanations for Machine Learning Models, TVCG 2020
Learning Global Transparent Models from Local Contrastive Explanations, NeurIPS 2020
Decisions, Counterfactual Explanations and Strategic Behavior, NeurIPS 2020
Algorithmic recourse under imperfect causal knowledge a probabilistic approach, NeurIPS 2020
Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recourses, NeurIPS 2020
Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision, ECCV 2020
Counterfactual Vision-and-Language Navigation via Adversarial Path Sampler, ECCV 2020
CERTIFAI: Counterfactual Explanations for Robustness, Transparency, Interpretability, and Fairness of Artificial Intelligence models, AAAI/AIES 2020
FACE: Feasible and Actionable Counterfactual Explanation, AAAI/AIES 2020
Counterfactual Explanations & Adversarial Examples, Arxiv preprint 2020
Instance-Based Counterfactual Explanations for Time Series Classification, Arxiv preprint 2020
On Relating 'Why?' and 'Why Not?' Explanations, Arxiv preprint 2020
Model extraction from counterfactual explanations, Arxiv preprint 2020
Efficient computation of counterfactual explanations of LVQ models, Arxiv preprint 2020
Plausible Counterfactuals: Auditing Deep Learning Classifiers with Realistic Adversarial Examples, Arxiv preprint 2020
ViCE: Visual Counterfactual Explanations for Machine Learning Models, IUI 2020
Model extraction from counterfactual explanations, Arxiv 2020
On the Fairness of Causal Algorithmic Recourse, Arxiv preprint 2020
Scaling Guarantees for Nearest Counterfactual Explanations, Arxiv preprint 2020
PermuteAttack: Counterfactual Explanation of Machine Learning Credit Scorecards, Arxiv preprint 2020
Decisions, Counterfactual Explanations and Strategic Behavior, Arxiv preprint 2020
FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles, Arxiv preprint 2020
Interpretable and Interactive Summaries of Actionable Recourses, Arxiv preprint 2020
Counterfactual Explanation Based on Gradual Construction for Deep Networks, Arxiv preprint 2020
CounteRGAN: Generating Realistic Counterfactuals with Residual Generative Adversarial Nets, Arxiv preprint 2020
EXPLAINABLE IMAGE CLASSIFICATION WITH EVIDENCE COUNTERFACTUAL, Arxiv preprint 2020
Model-Agnostic Counterfactual Explanations for Consequential Decisions, AISTATS 2020
Explaining Data-Driven Decisions made by AI Systems: The Counterfactual Approach, Arxiv preprint 2020
On the Fairness of Causal Algorithmic Recourse, Arxiv preprint 2020
On Counterfactual Explanations under Predictive Multiplicity, UAI 2020
EXPLANATION BY PROGRESSIVE EXAGGERATION, ICLR 2020
Algorithmic Recourse: from Counterfactual Explanations to Interventions, Arxiv preprint 2020
Learning Model-Agnostic Counterfactual Explanations for Tabular Data, ACM WWW 2020, code
The hidden assumptions behind counterfactual explanations and principal reasons, ACM Facct 2020
Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations, ACM Facct 2020
The philosophical basis of algorithmic recourse, ACM Facct 2020
Why Does My Model Fail? Contrastive Local Explanations for Retail Forecasting, ACM Facct 2020
Convex Density Constraints for Computing Plausible Counterfactual Explanations, ICANN 2020
Fast Real-time Counterfactual Explanations, ICML 2020 Workshop
CRUDS: Counterfactual Recourse Using Disentangled Subspaces, ICML 2020 Workshop
DACE: Distribution-Aware Counterfactual Explanation by Mixed-Integer Linear Optimization, IJCAI 2020
Relation-Based Counterfactual Explanations for Bayesian Network Classifiers, IJCAI 2020
PRINCE: Provider-side Interpretability with Counterfactual Explanations in Recommender Systems, WSDM 2020
CoCoX: Generating Conceptual and Counterfactual Explanations via Fault-Lines, AAAI 2020
SCOUT: Self-aware Discriminant Counterfactual Explanations, CVPR 2020, code
Multi-Objective Counterfactual Explanations, PPSN 2020
EMAP: Explanation by Minimal Adversarial Perturbation, AAAI 2020
Random forest explainability using counterfactual sets, Information Fusion 2020
The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations, IJCAI 2019
Multimodal Explanations by Predicting Counterfactuality in Videos, CVPR 2019
Unjustified Classification Regions and Counterfactual Explanations In Machine Learning, ECML-PDKK 2019
Factual and Counterfactual Explanations for Black Box Decision Making, IEEE Intelligent Systems 2019
Model Agnostic Contrastive Explanations for Structured Data, Arxiv preprint 2019
Counterfactuals uncover the modular structure of deep generative models, Arxiv preprint 2019
Actionable Interpretability through Optimizable Counterfactual Explanations for Tree Ensembles, arxiv preprint 2019
Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems, Arxiv preprint 2019
Generative Counterfactual Introspection for Explainable Deep Learning, Arxiv preprint 2019
Generating Counterfactual and Contrastive Explanations using SHAP, Arxiv preprint 2019
Interpretable Counterfactual Explanations Guided by Prototypes, Arxiv preprint 2019
Counterfactual Visual Explanations, ICML 2019
Counterfactual Explanation Algorithms for Behavioral and Textual Data, Arxiv preprint 2019
Synthesizing Action Sequences for Modifying Model Decisions, Arxiv preprint 2019
Measurable Counterfactual Local Explanations for Any Classifier, Arxiv preprint 2019
Generating Contrastive Explanations with Monotonic Attribute Functions, arxiv preprint 2019
The What-If Tool: Interactive Probing of Machine Learning Models, TVCG 2019
Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers, NeurIPS Workshop 2019
Actionable Recourse in Linear Classification, ACM Facct 2019
EQUALIZING RECOURSE ACROSS GROUPS, Arxiv preprint 2019
Efficient Search for Diverse Coherent Explanations, ACM Facct 2019
Counterfactual explanations of machine learning predictions: opportunities and challenges for AI safety, SafeAI@AAAI 2019
Explaining image classifiers by counterfactual generation, ICLR 2019
Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR, Hardvard Journal of Law & Technology 2018 (strong recommend)
Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives, NIPS 2018, code
Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections, NIPS 2018
Interpretable Credit Application Predictions With Counterfactual Explanations, Arxiv preprint 2018
Comparison-based Inverse Classification for Interpretability in Machine Learning, IPMU 2018
Generating Counterfactual Explanations with Natural Language, ICML 2018 Workshop
Grounding Visual Explanations, ECCV 2018
Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections, NeurIPS 2018
Inverse Classification for Comparison-based Interpretability in Machine Learning, Arxiv 2017
Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweaking, KDD 2017
When Worlds Collide: Integrating Different Counterfactual Assumptions in Fairness, NeurIPS 2017
A budget-constrained inverse classification framework for smooth classifiers, ICDMW 2017
Generalized Inverse Classification, SIAM 2017
Explaining Data-Driven Document Classifications, MIS Quarterly 2014
The Inverse Classification Problem, Journal of Computer Science and Technology 2010
The cost-minimizing inverse classification problem: a genetic algorithm approach, Decision Support Systems 2000
Alibi: https://github.com/SeldonIO/alibi
actionable-recourse: https://github.com/ustunb/actionable-recourse, Scikit-Learn
CEML: https://github.com/andreArtelt/ceml, Pytorch, Keras, Tensorflow, Scikit-Learn
Dice: https://github.com/interpretml/DiCE.git, Pytorch, TensorFlow
ContrastiveExplanation: https://github.com/MarcelRobeer/ContrastiveExplanation, scikit-learn,
cf-feasibility: https://github.com/divyat09/cf-feasibility, Pytorch, Tensorflow, Scikit-Learn,
Mace: https://github.com/amirhk/mace, Scikit-Learn,
Strategic-Decisions: https://github.com/Networks-Learning/strategic-decisions, Scikit-learn
Contrastive-Explanation-Method: https://github.com/IBM/Contrastive-Explanation-Method, Tensorflow
