REVIEW 26 cited by
Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Machine learning plays a role in many deployed decision systems, often in ways that are difficult or impossible to understand by human stakeholders. Explaining, in a human-understandable way, the relationship between the input and output of machine learning models is essential to the development of trustworthy machine learning based systems. A burgeoning body of research seeks to define the goals and methods of explainability in machine learning. In this paper, we seek to review and categorize research on counterfactual explanations, a specific class of explanation that provides a link between what could have happened had input to a model been changed in a particular way. Modern approaches to counterfactual explainability in machine learning draw connections to the established legal doctrine in many countries, making them appealing to fielded systems in high-impact areas such as finance and healthcare. Thus, we design a rubric with desirable properties of counterfactual explanation algorithms and comprehensively evaluate all currently proposed algorithms against that rubric. Our rubric provides easy comparison and comprehension of the advantages and disadvantages of different approaches and serves as an introduction to major research themes in this field. We also identify gaps and discuss promising research directions in the space of counterfactual explainability.
Forward citations
Cited by 26 Pith papers
-
Back to the Feature: Explaining Video Classifiers with Video Counterfactual Explanations
BTTF optimizes the initial noise of an image-to-video diffusion model using the target classifier's gradients to produce minimal counterfactual videos that explain video classifiers.
-
DCFO: Density-Based Counterfactuals for Outliers -- Additional Material
DCFO partitions the feature space by nearest-neighbour structure to make LOF scores differentiable, then uses gradient-based search to find the closest change that turns an outlier into an inlier.
-
Enhancing Interpretability and Effectiveness in Recommendation with Numerical Features via Learning to Contrast the Counterfactual samples
A plug-in contrastive loss that enforces monotonicity between numerical features and recommender outputs, via counterfactual sample synthesis, improves AUC, GAUC, and monotonicity.
-
VISION: Robust and Interpretable Code Vulnerability Detection Leveraging Counterfactual Augmentation
LLM-generated counterfactual code pairs with flipped vulnerability labels, used to train a GNN, sharply improve CWE-20 detection and attribution on the released CWE-20-CFA benchmark.
-
Are machine learning interpretations reliable? A stability study on global interpretations
Popular machine learning interpretation methods are frequently unstable under small data perturbations, and interpretation stability does not track prediction accuracy.
-
On Measuring Intrinsic Causal Attributions in Deep Neural Networks
Intrinsic causal contributions of input features to a neural network's output can be estimated from observational data via causal normalizing flows, and reduce to Sobol indices when inputs are independent.
-
Why Are You Wrong? Counterfactual Explanations for Language Grounding with 3D Objects
A method uses word-level sampling and a genetic algorithm to generate counterfactual utterances that flip a language-grounding model's wrong prediction to the correct one.
-
Towards Robust and Accurate Stability Estimation of Local Surrogate Models in Text-based Explainable AI
Many similarity measures used to judge adversarial text-XAI attacks are too sensitive, and synonymity-weighted variants change the measured success rates substantially.
-
Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAI
FreeMCG estimates on-manifold classifier gradients from black-box outputs using diffusion particles and an ensemble Kalman filter, and uses the same estimate for feature attribution and counterfactual explanation.
-
Private Counterfactual Retrieval With Immutable Features
Proposes two PIR-based protocols for retrieving the exact nearest counterfactual while keeping the user's immutable feature set private, with communication costs 6d+3M and 9(d+M).
-
AULLM++: Structured-Token-Conditioned Large Language Models for Micro-Expression Action Unit Detection
AULLM++ fuses multi-granularity visual tokens with FACS-prior AU graph instructions into an LLM prompt and uses counterfactual consistency training to improve micro-expression AU detection and cross-domain Macro-F1.
-
Negotiating Risk Boundaries in AI for Policing Through Mixed-Stakeholder Deliberation
A mixed-stakeholder UK workshop rated 13 AI policing use cases, rejecting recidivism risk assessment outright while accepting most others conditionally, and found that a racial-equity focus broadened, not narrowed, th...
-
Inferring Effects of Major Events through Discontinuity Forecasting of Population Anxiety
Discontinuity forecasting predicts a county's anxiety jump and slope change after a major event from pre-event trends, reaching out-of-sample correlations of about .76 and .87.
-
Explainable AI guided unsupervised fault diagnostics for high-voltage circuit breakers
An unsupervised framework detects, clusters, and explains circuit breaker faults from vibration and acoustic signals using only healthy data for training.
-
XplainAct: Visualization for Personalized Intervention Insights
XplainAct combines choropleth maps, LIME/SHAP local explanations, and nearest-neighbor subgrouping to simulate and interpret personalized interventions at the county level.
-
Integrating Probabilistic Trees and Causal Networks for Clinical and Epidemiological Data
PCF integrates causal Bayesian networks and probability-tree ensembles to deliver predictions plus intervention and counterfactual analysis on three healthcare datasets.
-
Graph Counterfactual Explainable AI via Latent Space Traversal
Counterfactual graph explanations are generated by gradient descent in the latent space of a permutation-equivariant graph VAE, steering the graph's encoding to the opposite class.
-
Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods
Explainable AI research should prioritize definitions, properties, evaluations, and actionability over new ad-hoc methods, on evidence from 617 papers and 34 practitioners.
-
Interpretable Event Diagnosis in Water Distribution Networks
Counterfactual fingerprints computed from sensor residuals can distinguish leakages from sensor faults in water distribution networks and provide operators with a contrastive explanation.
-
Integrating Explainable AI in Medical Devices: Technical, Clinical and Regulatory Insights and Recommendations
An MHRA-convened expert group and an eight-clinician pilot found that local explainable AI outputs improve trust and accuracy in heart attack risk predictions, while also exposing automation bias risks.
-
Model-Free Counterfactual Subset Selection at Scale
A one-pass streaming algorithm selects a diverse, relevant subset of real examples as counterfactual explanations, with a claimed 1/5.585 approximation guarantee and O(log k) update time.
-
Pareto Optimal Algorithmic Recourse in Multi-cost Function
A Bellman-Ford-style dynamic program over an actionability graph returns all Pareto-optimal recourse paths for multiple non-differentiable metric costs, with an epsilon-net sampling scheme proposed for scalability.
-
Integrating Evidence into the Design of XAI and AI-based Decision Support Systems: A Means-End Framework for End-users in Construction
A narrative review proposes a means-end framework that connects evidence hierarchies and evidential pluralism to the design of explainable AI decision support systems for construction.
-
Towards AI-$45^{\circ}$ Law: A Roadmap to Trustworthy AGI
The paper proposes the AI-45 degree law, a Causal Ladder framework, and five trustworthiness levels as a roadmap toward trustworthy AGI.
-
Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability
A survey of robustness and explainability methods for digital health AI, proposing a taxonomy and illustrating known XAI tools, without new empirical or theoretical results.
-
CoFE: A Framework Generating Counterfactual ECG for Explainable Cardiac AI-Diagnostics
CoFE edits ECG signals in a StyleGAN2 latent space so that an AI model changes its prediction, and the resulting feature changes match clinical signs for AF and hyperkalemia.
Discussion (0). Continue with ORCID to comment.